Project
Sanjay Kumar
2026-03-27
library(tidyverse)
library(dplyr)
library(ggplot2)
app_data <- read.csv("application_record.csv")
credit_data <- read.csv("credit_record.csv") Level 1: Understanding the Data(Basic Exploration)
Question 1.1 What is the structure(rows , columns and data types) of the application_record and credit_record?
cat("--- Application Record Structure ---")## --- Application Record Structure ---colnames(app_data)## [1] "ID" "CODE_GENDER" "FLAG_OWN_CAR"
## [4] "FLAG_OWN_REALTY" "CNT_CHILDREN" "AMT_INCOME_TOTAL"
## [7] "NAME_INCOME_TYPE" "NAME_EDUCATION_TYPE" "NAME_FAMILY_STATUS"
## [10] "NAME_HOUSING_TYPE" "DAYS_BIRTH" "DAYS_EMPLOYED"
## [13] "FLAG_MOBIL" "FLAG_WORK_PHONE" "FLAG_PHONE"
## [16] "FLAG_EMAIL" "OCCUPATION_TYPE" "CNT_FAM_MEMBERS"cat("--- Credit Record Structure ---")## --- Credit Record Structure ---colnames(credit_data)## [1] "ID" "MONTHS_BALANCE" "STATUS"str(app_data)## 'data.frame': 438557 obs. of 18 variables:
## $ ID : int 5008804 5008805 5008806 5008808 5008809 5008810 5008811 5008812 5008813 5008814 ...
## $ CODE_GENDER : chr "M" "M" "M" "F" ...
## $ FLAG_OWN_CAR : chr "Y" "Y" "Y" "N" ...
## $ FLAG_OWN_REALTY : chr "Y" "Y" "Y" "Y" ...
## $ CNT_CHILDREN : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AMT_INCOME_TOTAL : num 427500 427500 112500 270000 270000 ...
## $ NAME_INCOME_TYPE : chr "Working" "Working" "Working" "Commercial associate" ...
## $ NAME_EDUCATION_TYPE: chr "Higher education" "Higher education" "Secondary / secondary special" "Secondary / secondary special" ...
## $ NAME_FAMILY_STATUS : chr "Civil marriage" "Civil marriage" "Married" "Single / not married" ...
## $ NAME_HOUSING_TYPE : chr "Rented apartment" "Rented apartment" "House / apartment" "House / apartment" ...
## $ DAYS_BIRTH : int -12005 -12005 -21474 -19110 -19110 -19110 -19110 -22464 -22464 -22464 ...
## $ DAYS_EMPLOYED : int -4542 -4542 -1134 -3051 -3051 -3051 -3051 365243 365243 365243 ...
## $ FLAG_MOBIL : int 1 1 1 1 1 1 1 1 1 1 ...
## $ FLAG_WORK_PHONE : int 1 1 0 0 0 0 0 0 0 0 ...
## $ FLAG_PHONE : int 0 0 0 1 1 1 1 0 0 0 ...
## $ FLAG_EMAIL : int 0 0 0 1 1 1 1 0 0 0 ...
## $ OCCUPATION_TYPE : chr "" "" "Security staff" "Sales staff" ...
## $ CNT_FAM_MEMBERS : num 2 2 2 1 1 1 1 1 1 1 ...str(credit_data)## 'data.frame': 1048575 obs. of 3 variables:
## $ ID : int 5001711 5001711 5001711 5001711 5001712 5001712 5001712 5001712 5001712 5001712 ...
## $ MONTHS_BALANCE: int 0 -1 -2 -3 0 -1 -2 -3 -4 -5 ...
## $ STATUS : chr "X" "0" "0" "0" ...Interpretation: The initial exploration of the datasets reveals a relational structure between the applicant demographics and their credit history.
Application Record: This dataset contains 438,557 records with 18 variables. It includes categorical data such as Gender, Education, and Housing type, alongside numerical data like Income and Family member counts.
Credit Record: The dataset contains 1,048,575 records with 3 specific variables. It includes numerical data such as
MONTHS_BALANCEand categorical data in theSTATUScolumn.
Question 1.2: How many missing values exist in each dataset, and
what is the percentage of missing data in
OCCUPATION_TYPE?
# Checking for missing values in Application dataset
colSums(is.na(app_data))## ID CODE_GENDER FLAG_OWN_CAR FLAG_OWN_REALTY
## 0 0 0 0
## CNT_CHILDREN AMT_INCOME_TOTAL NAME_INCOME_TYPE NAME_EDUCATION_TYPE
## 0 0 0 0
## NAME_FAMILY_STATUS NAME_HOUSING_TYPE DAYS_BIRTH DAYS_EMPLOYED
## 0 0 0 0
## FLAG_MOBIL FLAG_WORK_PHONE FLAG_PHONE FLAG_EMAIL
## 0 0 0 0
## OCCUPATION_TYPE CNT_FAM_MEMBERS
## 0 0# Checking for missing values in Application dataset
colSums(is.na(credit_data))## ID MONTHS_BALANCE STATUS
## 0 0 0# Calculating the percentage of missing values in `OCCUPATION_TYPE`
occ_missing_count <- sum(app_data$OCCUPATION_TYPE == "" | is.na(app_data$OCCUPATION_TYPE))
occ_missing_percentage <- (occ_missing_count/nrow(app_data)) *100
cat("No. of misssing values:",occ_missing_count)## No. of misssing values: 134203cat("\nPercentage of missing values:",occ_missing_percentage)##
## Percentage of missing values: 30.60104- Interpretation:The missing value audit is a crucial step in ensuring data quality before performing any advanced analytics or modeling.
- Application Record: There are no NA-type missing
values in the primary demographic columns.However, the
OCCUPATION_TYPEcolumn contains a significant number of empty strings (““).Approximately 30.62% of applicants have not specified their occupation.
Queston 1.3: How many unique Customer IDs are present in both datasets, and how many overlap?
# 1. Unique IDs
unique_app_ids <- n_distinct(app_data$ID)
unique_credit_ids <- n_distinct(credit_data$ID)
cat("Unique IDs in Application Record:", unique_app_ids, "\n")## Unique IDs in Application Record: 438510cat("Unique IDs in Credit Record:", unique_credit_ids)## Unique IDs in Credit Record: 45985# 2. Overlapping IDs
common_ids <- length(intersect(app_data$ID, credit_data$ID))
cat("Common IDs :", common_ids)## Common IDs : 36457- Interpretation:The identification of unique records and their intersection is critical for defining the scope of our predictive modeling:There are 438510 unique applicant profiles available in the application Record.We have payment history data for 45985 unique customers.Only 36457 individuals exist in both datasets simultaneously.This overlap represents our actual working population.
Queston 1.4: What are the different categories of the
STATUS column, and which one occurs most frequently?
status_counts <- table(credit_data$STATUS)
print(status_counts)##
## 0 1 2 3 4 5 C X
## 383120 11090 868 320 223 1693 442031 209230most_common_status <- names(which.max(status_counts))
most_common_value <- max(status_counts)
cat("\nThe most frequently category status:",most_common_status,"\n")##
## The most frequently category status: Ccat("The most common values:", most_common_value)## The most common values: 442031- Interpretation: The
STATUSis the most important variable of our credit risk analysis its define the payment behaviour of each amount.The column have 8 distinct categories:0,1,2,3,4,5,C and X. - Meaning of status:
- ‘C’(Closed) and ‘X’(No debit) indicate healthy accounts.
- ‘0’to’5’ represent the severity of payment delays (by increasing the 0 to 5 it represents the no. of days delayed in the payment 1-29 days for 0 and over 150 days for 5 ).
Question 1.5: Are there any duplicate IDs in the applicaton_record that need to be removed?
duplicate_ids_count <- sum(duplicated(app_data$ID))
cat("Total duplicate CUstomer IDs found:",duplicate_ids_count)## Total duplicate CUstomer IDs found: 47app_data <-app_data %>% distinct(ID , .keep_all = TRUE)
nrow(app_data)## [1] 438510- Interpretation:Duplicate entries can lead to
statistical bias and “Data Leakage” where the model
learns from the same person’s information multiple times.Our initial
audit revealed 47 duplicate Customer IDs within the
application dataset.We utilized the
distinct()function to remove these redundant entries.After the cleaning process, the record count decreased from 438,557 to 438,510 unique entries.
This step ensures a “One ID = One Customer”relationship. Establishing a unique primary key is essential before we merge datasets or begin the predictive modeling phase, as it ensures that each applicant’s profile is weighed accurately.
Level 2: Data Extraction & Filtering or Data Pre-processing
Question 2.1: Perform a filtered extraction to identify the top 10
applicants with the highest reported AMT_INCOME_TOTAL for
wealth-ter analysis.
top_ten_income <- app_data %>%
arrange(desc(AMT_INCOME_TOTAL)) %>%
head(10)
print(top_ten_income)## ID CODE_GENDER FLAG_OWN_CAR FLAG_OWN_REALTY CNT_CHILDREN
## 1 5987963 M Y N 0
## 2 5987964 M Y N 0
## 3 5987966 M Y N 0
## 4 5987967 M Y N 0
## 5 5987968 M Y N 0
## 6 5987969 M Y N 0
## 7 7987964 M Y N 0
## 8 6123707 M Y Y 0
## 9 6123708 M Y Y 0
## 10 6123709 M Y Y 0
## AMT_INCOME_TOTAL NAME_INCOME_TYPE NAME_EDUCATION_TYPE NAME_FAMILY_STATUS
## 1 6750000 Working Higher education Married
## 2 6750000 Working Higher education Married
## 3 6750000 Working Higher education Married
## 4 6750000 Working Higher education Married
## 5 6750000 Working Higher education Married
## 6 6750000 Working Higher education Married
## 7 6750000 Working Higher education Married
## 8 4500000 Working Higher education Married
## 9 4500000 Working Higher education Married
## 10 4500000 Working Higher education Married
## NAME_HOUSING_TYPE DAYS_BIRTH DAYS_EMPLOYED FLAG_MOBIL FLAG_WORK_PHONE
## 1 House / apartment -19341 -443 1 1
## 2 House / apartment -19341 -443 1 1
## 3 House / apartment -19341 -443 1 1
## 4 House / apartment -19341 -443 1 1
## 5 House / apartment -19341 -443 1 1
## 6 House / apartment -19341 -443 1 1
## 7 House / apartment -19341 -443 1 1
## 8 House / apartment -18784 -3618 1 1
## 9 House / apartment -18784 -3618 1 1
## 10 House / apartment -18784 -3618 1 1
## FLAG_PHONE FLAG_EMAIL OCCUPATION_TYPE CNT_FAM_MEMBERS
## 1 1 0 Laborers 2
## 2 1 0 Laborers 2
## 3 1 0 Laborers 2
## 4 1 0 Laborers 2
## 5 1 0 Laborers 2
## 6 1 0 Laborers 2
## 7 1 0 Laborers 2
## 8 0 0 Managers 2
## 9 0 0 Managers 2
## 10 0 0 Managers 2- Interpretation: The extraction of high-income individuals is a vital step in segmenting the customer base for premium banking services:- High-income segments are often prioritized for higher credit limits and premium cards, as their capacity to repay is statistically superior.
Question 2.2: Filter the records for high-asset applicants who own both a car and reality while supporting more than 2 children.
# Applying Multiple conditions
# flag_own_car == 'Y' # Car owner
# flag_own_realty == 'Y' # House Owner
# cnt_children > 2 (more than two children)
high_asset_familes <- app_data %>%
filter(FLAG_OWN_CAR == "Y" & FLAG_OWN_REALTY == 'Y' & CNT_CHILDREN >2)
cat("TOtal high asset families found:", nrow(high_asset_familes))## TOtal high asset families found: 2069head(high_asset_familes[, c("ID","FLAG_OWN_CAR", "FLAG_OWN_REALTY", "CNT_CHILDREN", "AMT_INCOME_TOTAL")])## ID FLAG_OWN_CAR FLAG_OWN_REALTY CNT_CHILDREN AMT_INCOME_TOTAL
## 1 5008836 Y Y 3 270000
## 2 5008837 Y Y 3 270000
## 3 5021339 Y Y 3 270000
## 4 5021340 Y Y 3 270000
## 5 5021341 Y Y 3 270000
## 6 5021342 Y Y 3 270000- Interpretation:By focusing on applicants who own both a car and reality, we are identifying individuals with high collateral value, which is a positive indicator for credit recovery.This segment is ideal for specialized family-oriented financial products or high-limit credit lines due to their established asset base.
Question 2.3: Extract all demographic records for
"Pensioners" who are currently living in “Rented
apartments” to assess housing stability.
pensioners_rented <- app_data %>%
filter(NAME_INCOME_TYPE == 'Pensioner' & NAME_HOUSING_TYPE == "Rented apartment")
pensioners_rented## ID CODE_GENDER FLAG_OWN_CAR FLAG_OWN_REALTY CNT_CHILDREN
## 1 5009033 F N N 0
## 2 5009034 F N N 0
## 3 5009035 F N N 0
## 4 5009036 F N N 0
## 5 5009037 F N N 0
## 6 5009038 F N N 0
## 7 5009592 F N N 0
## 8 5090748 F N N 0
## 9 5024876 F Y Y 0
## 10 6063350 F Y Y 0
## 11 6063351 F Y Y 0
## 12 6063352 F Y Y 0
## 13 6063353 F Y Y 0
## 14 5052757 F N Y 0
## 15 5052758 F N Y 0
## 16 5087864 F Y Y 0
## 17 5087865 F Y Y 0
## 18 5087866 F Y Y 0
## 19 5090645 F N Y 0
## 20 5791715 F N Y 0
## 21 5791716 F N Y 0
## 22 5791717 F N Y 0
## 23 5791718 F N Y 0
## 24 5791719 F N Y 0
## 25 5791720 F N Y 0
## 26 5791721 F N Y 0
## 27 5791722 F N Y 0
## 28 5791723 F N Y 0
## 29 5091910 F N Y 0
## 30 5513299 F N Y 0
## 31 5115562 M N Y 0
## 32 5115563 M N Y 0
## 33 5115564 M N Y 0
## 34 5115565 M N Y 0
## 35 5115566 M N Y 0
## 36 5115567 M N Y 0
## 37 5115568 M N Y 0
## 38 5115571 M N Y 0
## 39 5115572 M N Y 0
## 40 5115573 M N Y 0
## 41 5115574 M N Y 0
## 42 5116264 F N Y 0
## 43 5116266 F N Y 0
## 44 5116267 F N Y 0
## 45 5177428 F N Y 0
## 46 5177429 F N Y 0
## 47 5177872 F N Y 0
## 48 5177873 F N Y 0
## 49 5279529 F N Y 0
## 50 5279530 F N Y 0
## 51 5279531 F N Y 0
## 52 5279532 F N Y 0
## 53 5279533 F N Y 0
## 54 5279534 F N Y 0
## 55 5279535 F N Y 0
## 56 6268956 F N Y 0
## 57 5290729 M N N 1
## 58 5876688 M N N 1
## 59 5876689 M N N 1
## 60 5876690 M N N 1
## 61 5403340 F N Y 0
## 62 5403341 F N Y 0
## 63 5403342 F N Y 0
## 64 5403343 F N Y 0
## 65 5405297 F N N 0
## 66 5405298 F N N 0
## 67 5565711 F N N 0
## 68 5541487 F N Y 0
## 69 5541488 F N Y 0
## 70 5541490 F N Y 0
## 71 5541491 F N Y 0
## 72 5541492 F N Y 0
## 73 5541493 F N Y 0
## 74 5541495 F N Y 0
## 75 5541496 F N Y 0
## 76 5541497 F N Y 0
## 77 5541498 F N Y 0
## 78 5541499 F N Y 0
## 79 5626559 F N N 0
## 80 5626560 F N N 0
## 81 5626561 F N N 0
## 82 5627319 F N Y 0
## 83 5627320 F N Y 0
## 84 6007579 F N Y 0
## 85 6007580 F N Y 0
## 86 5668131 F N N 0
## 87 5707096 F N Y 0
## 88 5707097 F N Y 0
## 89 5707098 F N Y 0
## 90 5707099 F N Y 0
## 91 5707100 F N Y 0
## 92 5707101 F N Y 0
## 93 5707102 F N Y 0
## 94 5707103 F N Y 0
## 95 5707104 F N Y 0
## 96 5707105 F N Y 0
## 97 5707106 F N Y 0
## 98 5707107 F N Y 0
## 99 5707108 F N Y 0
## 100 5707109 F N Y 0
## 101 5713030 F N Y 0
## 102 5713819 M N N 0
## 103 5739421 F N Y 0
## 104 5739422 F N Y 0
## 105 6099143 F N Y 0
## 106 6099144 F N Y 0
## 107 5808141 F N Y 0
## 108 5808142 F N Y 0
## 109 5808143 F N Y 0
## 110 5808144 F N Y 0
## 111 5808145 F N Y 0
## 112 5808146 F N Y 0
## 113 5872918 M Y N 0
## 114 6806204 M Y N 0
## 115 6806205 M Y N 0
## 116 6806206 M Y N 0
## 117 6806207 M Y N 0
## 118 5877642 F N N 0
## 119 5877643 F N N 0
## 120 5877644 F N N 0
## 121 5888706 F N Y 0
## 122 5888708 F N Y 0
## 123 5888709 F N Y 0
## 124 5929281 F N Y 0
## 125 5929282 F N Y 0
## 126 5929283 F N Y 0
## 127 5944649 M N N 3
## 128 5944650 M N N 3
## 129 5944651 M N N 3
## 130 5944652 M N N 3
## 131 5957938 M N N 0
## 132 5969574 F N Y 0
## 133 6007217 F Y Y 0
## 134 6586225 F Y Y 0
## 135 6586226 F Y Y 0
## 136 6586227 F Y Y 0
## 137 6586228 F Y Y 0
## 138 6008211 F N Y 0
## 139 6008212 F N Y 0
## 140 6008213 F N Y 0
## 141 6008214 F N Y 0
## 142 6014539 F Y Y 0
## 143 6014540 F Y Y 0
## 144 6037327 M N Y 0
## 145 6037328 M N Y 0
## 146 6037329 M N Y 0
## 147 6037330 M N Y 0
## 148 6037331 M N Y 0
## 149 6054391 M Y Y 0
## 150 6054392 M Y Y 0
## 151 6054393 M Y Y 0
## 152 6073730 F N N 0
## 153 6684305 F N N 0
## 154 6684306 F N N 0
## 155 6684307 F N N 0
## 156 6684308 F N N 0
## 157 6088149 F N N 0
## 158 6088150 F N N 0
## 159 6088151 F N N 0
## 160 6088152 F N N 0
## 161 6088153 F N N 0
## 162 6088154 F N N 0
## 163 6088155 F N N 0
## 164 6088156 F N N 0
## 165 6088157 F N N 0
## 166 6088158 F N N 0
## 167 6148226 F N Y 0
## 168 6148227 F N Y 0
## 169 6230408 F N Y 0
## 170 6230409 F N Y 0
## 171 6230411 F N Y 0
## 172 6230412 F N Y 0
## 173 6230413 F N Y 0
## 174 6230414 F N Y 0
## 175 6230417 F N Y 0
## 176 6230418 F N Y 0
## 177 6230419 F N Y 0
## 178 6230422 F N Y 0
## 179 6230423 F N Y 0
## 180 6230424 F N Y 0
## 181 6230425 F N Y 0
## 182 6230426 F N Y 0
## 183 6230427 F N Y 0
## 184 6230428 F N Y 0
## 185 6230429 F N Y 0
## 186 6240975 F N N 1
## 187 6240976 F N N 1
## 188 6240977 F N N 1
## 189 6264617 F N Y 1
## 190 6336049 F N Y 1
## 191 6336050 F N Y 1
## 192 6336051 F N Y 1
## 193 6336053 F N Y 1
## 194 6280517 F N N 0
## 195 6280518 F N N 0
## 196 6375585 F N N 0
## 197 6375586 F N N 0
## 198 6375587 F N N 0
## 199 6375588 F N N 0
## 200 6375590 F N N 0
## 201 6375591 F N N 0
## 202 6375593 F N N 0
## 203 6375594 F N N 0
## 204 6397321 F N Y 0
## 205 6397322 F N Y 0
## 206 6410106 F N Y 0
## 207 6424262 F N N 0
## 208 6424263 F N N 0
## 209 6424264 F N N 0
## 210 6424265 F N N 0
## 211 6424266 F N N 0
## 212 6424267 F N N 0
## 213 6424268 F N N 0
## 214 6424269 F N N 0
## 215 6424270 F N N 0
## 216 6424271 F N N 0
## 217 6424272 F N N 0
## 218 6424273 F N N 0
## 219 6424274 F N N 0
## 220 6424275 F N N 0
## 221 6424276 F N N 0
## 222 6424277 F N N 0
## 223 6424278 F N N 0
## 224 6424279 F N N 0
## 225 6424280 F N N 0
## 226 6425392 F N N 0
## 227 6425393 F N N 0
## 228 6425394 F N N 0
## 229 6830653 F N N 0
## 230 6830654 F N N 0
## 231 6830655 F N N 0
## 232 6830656 F N N 0
## 233 6830658 F N N 0
## 234 6830659 F N N 0
## 235 6830660 F N N 0
## 236 6830661 F N N 0
## 237 6830662 F N N 0
## 238 6830663 F N N 0
## 239 6830664 F N N 0
## 240 6830666 F N N 0
## 241 6830667 F N N 0
## 242 6830668 F N N 0
## 243 6830669 F N N 0
## 244 6830670 F N N 0
## 245 6830671 F N N 0
## 246 6830672 F N N 0
## 247 6830673 F N N 0
## 248 6830674 F N N 0
## 249 6830675 F N N 0
## 250 6830676 F N N 0
## 251 6830677 F N N 0
## 252 6830679 F N N 0
## 253 6429545 F N Y 0
## 254 6429547 F N Y 0
## 255 6429550 F N Y 0
## 256 6519201 F N Y 0
## 257 6519202 F N Y 0
## 258 6528317 F N Y 0
## 259 6528318 F N Y 0
## 260 6528319 F N Y 0
## 261 6528320 F N Y 0
## 262 6528321 F N Y 0
## 263 6528322 F N Y 0
## 264 6528323 F N Y 0
## 265 6528324 F N Y 0
## 266 6528325 F N Y 0
## 267 6528326 F N Y 0
## 268 6529595 M N N 0
## 269 6605845 M N N 0
## 270 6625464 F N N 0
## 271 6625465 F N N 0
## 272 6625466 F N N 0
## 273 6661353 F Y N 1
## 274 6661354 F Y N 1
## 275 6661355 F Y N 1
## 276 6661356 F Y N 1
## 277 6661357 F Y N 1
## 278 6661358 F Y N 1
## 279 7424274 F N N 0
## 280 7230417 F N Y 0
## 281 7007579 F N Y 0
## 282 7888709 F N Y 0
## 283 7424270 F N N 0
## 284 7888706 F N Y 0
## 285 7230418 F N Y 0
## 286 7872918 M Y N 0
## 287 5400793 M N Y 0
## 288 6116043 M Y Y 0
## 289 6560405 F N N 0
## AMT_INCOME_TOTAL NAME_INCOME_TYPE NAME_EDUCATION_TYPE
## 1 255150 Pensioner Incomplete higher
## 2 255150 Pensioner Incomplete higher
## 3 255150 Pensioner Incomplete higher
## 4 255150 Pensioner Incomplete higher
## 5 255150 Pensioner Incomplete higher
## 6 255150 Pensioner Incomplete higher
## 7 112500 Pensioner Secondary / secondary special
## 8 112500 Pensioner Secondary / secondary special
## 9 211500 Pensioner Secondary / secondary special
## 10 211500 Pensioner Secondary / secondary special
## 11 211500 Pensioner Secondary / secondary special
## 12 211500 Pensioner Secondary / secondary special
## 13 211500 Pensioner Secondary / secondary special
## 14 126000 Pensioner Secondary / secondary special
## 15 126000 Pensioner Secondary / secondary special
## 16 112500 Pensioner Secondary / secondary special
## 17 112500 Pensioner Secondary / secondary special
## 18 112500 Pensioner Secondary / secondary special
## 19 144000 Pensioner Secondary / secondary special
## 20 144000 Pensioner Secondary / secondary special
## 21 144000 Pensioner Secondary / secondary special
## 22 144000 Pensioner Secondary / secondary special
## 23 144000 Pensioner Secondary / secondary special
## 24 144000 Pensioner Secondary / secondary special
## 25 144000 Pensioner Secondary / secondary special
## 26 144000 Pensioner Secondary / secondary special
## 27 144000 Pensioner Secondary / secondary special
## 28 144000 Pensioner Secondary / secondary special
## 29 157500 Pensioner Secondary / secondary special
## 30 157500 Pensioner Secondary / secondary special
## 31 126000 Pensioner Secondary / secondary special
## 32 126000 Pensioner Secondary / secondary special
## 33 126000 Pensioner Secondary / secondary special
## 34 126000 Pensioner Secondary / secondary special
## 35 126000 Pensioner Secondary / secondary special
## 36 126000 Pensioner Secondary / secondary special
## 37 126000 Pensioner Secondary / secondary special
## 38 126000 Pensioner Secondary / secondary special
## 39 126000 Pensioner Secondary / secondary special
## 40 126000 Pensioner Secondary / secondary special
## 41 126000 Pensioner Secondary / secondary special
## 42 139500 Pensioner Secondary / secondary special
## 43 139500 Pensioner Secondary / secondary special
## 44 139500 Pensioner Secondary / secondary special
## 45 360000 Pensioner Secondary / secondary special
## 46 360000 Pensioner Secondary / secondary special
## 47 247500 Pensioner Secondary / secondary special
## 48 247500 Pensioner Secondary / secondary special
## 49 202500 Pensioner Secondary / secondary special
## 50 202500 Pensioner Secondary / secondary special
## 51 202500 Pensioner Secondary / secondary special
## 52 202500 Pensioner Secondary / secondary special
## 53 202500 Pensioner Secondary / secondary special
## 54 202500 Pensioner Secondary / secondary special
## 55 202500 Pensioner Secondary / secondary special
## 56 202500 Pensioner Secondary / secondary special
## 57 319500 Pensioner Secondary / secondary special
## 58 319500 Pensioner Secondary / secondary special
## 59 319500 Pensioner Secondary / secondary special
## 60 319500 Pensioner Secondary / secondary special
## 61 112500 Pensioner Secondary / secondary special
## 62 112500 Pensioner Secondary / secondary special
## 63 112500 Pensioner Secondary / secondary special
## 64 112500 Pensioner Secondary / secondary special
## 65 135000 Pensioner Higher education
## 66 135000 Pensioner Higher education
## 67 135000 Pensioner Higher education
## 68 74250 Pensioner Secondary / secondary special
## 69 74250 Pensioner Secondary / secondary special
## 70 74250 Pensioner Secondary / secondary special
## 71 74250 Pensioner Secondary / secondary special
## 72 74250 Pensioner Secondary / secondary special
## 73 74250 Pensioner Secondary / secondary special
## 74 74250 Pensioner Secondary / secondary special
## 75 74250 Pensioner Secondary / secondary special
## 76 74250 Pensioner Secondary / secondary special
## 77 74250 Pensioner Secondary / secondary special
## 78 74250 Pensioner Secondary / secondary special
## 79 202500 Pensioner Secondary / secondary special
## 80 202500 Pensioner Secondary / secondary special
## 81 202500 Pensioner Secondary / secondary special
## 82 112500 Pensioner Secondary / secondary special
## 83 112500 Pensioner Secondary / secondary special
## 84 112500 Pensioner Secondary / secondary special
## 85 112500 Pensioner Secondary / secondary special
## 86 162000 Pensioner Secondary / secondary special
## 87 247500 Pensioner Higher education
## 88 247500 Pensioner Higher education
## 89 247500 Pensioner Higher education
## 90 247500 Pensioner Higher education
## 91 247500 Pensioner Higher education
## 92 247500 Pensioner Higher education
## 93 247500 Pensioner Higher education
## 94 247500 Pensioner Higher education
## 95 247500 Pensioner Higher education
## 96 247500 Pensioner Higher education
## 97 247500 Pensioner Higher education
## 98 247500 Pensioner Higher education
## 99 247500 Pensioner Higher education
## 100 247500 Pensioner Higher education
## 101 157500 Pensioner Secondary / secondary special
## 102 32139 Pensioner Secondary / secondary special
## 103 157500 Pensioner Secondary / secondary special
## 104 157500 Pensioner Secondary / secondary special
## 105 157500 Pensioner Secondary / secondary special
## 106 157500 Pensioner Secondary / secondary special
## 107 90000 Pensioner Secondary / secondary special
## 108 90000 Pensioner Secondary / secondary special
## 109 90000 Pensioner Secondary / secondary special
## 110 90000 Pensioner Secondary / secondary special
## 111 90000 Pensioner Secondary / secondary special
## 112 90000 Pensioner Secondary / secondary special
## 113 382500 Pensioner Higher education
## 114 382500 Pensioner Higher education
## 115 382500 Pensioner Higher education
## 116 382500 Pensioner Higher education
## 117 382500 Pensioner Higher education
## 118 180000 Pensioner Secondary / secondary special
## 119 180000 Pensioner Secondary / secondary special
## 120 180000 Pensioner Secondary / secondary special
## 121 112500 Pensioner Secondary / secondary special
## 122 112500 Pensioner Secondary / secondary special
## 123 112500 Pensioner Secondary / secondary special
## 124 135000 Pensioner Secondary / secondary special
## 125 135000 Pensioner Secondary / secondary special
## 126 135000 Pensioner Secondary / secondary special
## 127 337500 Pensioner Secondary / secondary special
## 128 337500 Pensioner Secondary / secondary special
## 129 337500 Pensioner Secondary / secondary special
## 130 337500 Pensioner Secondary / secondary special
## 131 157500 Pensioner Secondary / secondary special
## 132 45000 Pensioner Secondary / secondary special
## 133 247500 Pensioner Lower secondary
## 134 247500 Pensioner Lower secondary
## 135 247500 Pensioner Lower secondary
## 136 247500 Pensioner Lower secondary
## 137 247500 Pensioner Lower secondary
## 138 112500 Pensioner Secondary / secondary special
## 139 112500 Pensioner Secondary / secondary special
## 140 112500 Pensioner Secondary / secondary special
## 141 112500 Pensioner Secondary / secondary special
## 142 73350 Pensioner Secondary / secondary special
## 143 73350 Pensioner Secondary / secondary special
## 144 121500 Pensioner Secondary / secondary special
## 145 121500 Pensioner Secondary / secondary special
## 146 121500 Pensioner Secondary / secondary special
## 147 121500 Pensioner Secondary / secondary special
## 148 121500 Pensioner Secondary / secondary special
## 149 135000 Pensioner Secondary / secondary special
## 150 135000 Pensioner Secondary / secondary special
## 151 135000 Pensioner Secondary / secondary special
## 152 135000 Pensioner Secondary / secondary special
## 153 135000 Pensioner Secondary / secondary special
## 154 135000 Pensioner Secondary / secondary special
## 155 135000 Pensioner Secondary / secondary special
## 156 135000 Pensioner Secondary / secondary special
## 157 135000 Pensioner Secondary / secondary special
## 158 135000 Pensioner Secondary / secondary special
## 159 135000 Pensioner Secondary / secondary special
## 160 135000 Pensioner Secondary / secondary special
## 161 135000 Pensioner Secondary / secondary special
## 162 135000 Pensioner Secondary / secondary special
## 163 135000 Pensioner Secondary / secondary special
## 164 135000 Pensioner Secondary / secondary special
## 165 135000 Pensioner Secondary / secondary special
## 166 135000 Pensioner Secondary / secondary special
## 167 162000 Pensioner Secondary / secondary special
## 168 162000 Pensioner Secondary / secondary special
## 169 162000 Pensioner Secondary / secondary special
## 170 162000 Pensioner Secondary / secondary special
## 171 162000 Pensioner Secondary / secondary special
## 172 162000 Pensioner Secondary / secondary special
## 173 162000 Pensioner Secondary / secondary special
## 174 162000 Pensioner Secondary / secondary special
## 175 162000 Pensioner Secondary / secondary special
## 176 162000 Pensioner Secondary / secondary special
## 177 162000 Pensioner Secondary / secondary special
## 178 162000 Pensioner Secondary / secondary special
## 179 162000 Pensioner Secondary / secondary special
## 180 162000 Pensioner Secondary / secondary special
## 181 162000 Pensioner Secondary / secondary special
## 182 162000 Pensioner Secondary / secondary special
## 183 162000 Pensioner Secondary / secondary special
## 184 162000 Pensioner Secondary / secondary special
## 185 162000 Pensioner Secondary / secondary special
## 186 403650 Pensioner Secondary / secondary special
## 187 403650 Pensioner Secondary / secondary special
## 188 403650 Pensioner Secondary / secondary special
## 189 292500 Pensioner Secondary / secondary special
## 190 292500 Pensioner Secondary / secondary special
## 191 292500 Pensioner Secondary / secondary special
## 192 292500 Pensioner Secondary / secondary special
## 193 292500 Pensioner Secondary / secondary special
## 194 157500 Pensioner Secondary / secondary special
## 195 157500 Pensioner Secondary / secondary special
## 196 121500 Pensioner Secondary / secondary special
## 197 121500 Pensioner Secondary / secondary special
## 198 121500 Pensioner Secondary / secondary special
## 199 121500 Pensioner Secondary / secondary special
## 200 121500 Pensioner Secondary / secondary special
## 201 121500 Pensioner Secondary / secondary special
## 202 121500 Pensioner Secondary / secondary special
## 203 121500 Pensioner Secondary / secondary special
## 204 135000 Pensioner Secondary / secondary special
## 205 135000 Pensioner Secondary / secondary special
## 206 135000 Pensioner Secondary / secondary special
## 207 103500 Pensioner Secondary / secondary special
## 208 103500 Pensioner Secondary / secondary special
## 209 103500 Pensioner Secondary / secondary special
## 210 103500 Pensioner Secondary / secondary special
## 211 103500 Pensioner Secondary / secondary special
## 212 103500 Pensioner Secondary / secondary special
## 213 103500 Pensioner Secondary / secondary special
## 214 103500 Pensioner Secondary / secondary special
## 215 103500 Pensioner Secondary / secondary special
## 216 103500 Pensioner Secondary / secondary special
## 217 103500 Pensioner Secondary / secondary special
## 218 103500 Pensioner Secondary / secondary special
## 219 103500 Pensioner Secondary / secondary special
## 220 103500 Pensioner Secondary / secondary special
## 221 103500 Pensioner Secondary / secondary special
## 222 103500 Pensioner Secondary / secondary special
## 223 103500 Pensioner Secondary / secondary special
## 224 103500 Pensioner Secondary / secondary special
## 225 103500 Pensioner Secondary / secondary special
## 226 72000 Pensioner Secondary / secondary special
## 227 72000 Pensioner Secondary / secondary special
## 228 72000 Pensioner Secondary / secondary special
## 229 72000 Pensioner Secondary / secondary special
## 230 72000 Pensioner Secondary / secondary special
## 231 72000 Pensioner Secondary / secondary special
## 232 72000 Pensioner Secondary / secondary special
## 233 72000 Pensioner Secondary / secondary special
## 234 72000 Pensioner Secondary / secondary special
## 235 72000 Pensioner Secondary / secondary special
## 236 72000 Pensioner Secondary / secondary special
## 237 72000 Pensioner Secondary / secondary special
## 238 72000 Pensioner Secondary / secondary special
## 239 72000 Pensioner Secondary / secondary special
## 240 72000 Pensioner Secondary / secondary special
## 241 72000 Pensioner Secondary / secondary special
## 242 72000 Pensioner Secondary / secondary special
## 243 72000 Pensioner Secondary / secondary special
## 244 72000 Pensioner Secondary / secondary special
## 245 72000 Pensioner Secondary / secondary special
## 246 72000 Pensioner Secondary / secondary special
## 247 72000 Pensioner Secondary / secondary special
## 248 72000 Pensioner Secondary / secondary special
## 249 72000 Pensioner Secondary / secondary special
## 250 72000 Pensioner Secondary / secondary special
## 251 72000 Pensioner Secondary / secondary special
## 252 72000 Pensioner Secondary / secondary special
## 253 180000 Pensioner Secondary / secondary special
## 254 180000 Pensioner Secondary / secondary special
## 255 180000 Pensioner Secondary / secondary special
## 256 135000 Pensioner Secondary / secondary special
## 257 135000 Pensioner Secondary / secondary special
## 258 180000 Pensioner Secondary / secondary special
## 259 180000 Pensioner Secondary / secondary special
## 260 180000 Pensioner Secondary / secondary special
## 261 180000 Pensioner Secondary / secondary special
## 262 180000 Pensioner Secondary / secondary special
## 263 180000 Pensioner Secondary / secondary special
## 264 180000 Pensioner Secondary / secondary special
## 265 180000 Pensioner Secondary / secondary special
## 266 180000 Pensioner Secondary / secondary special
## 267 180000 Pensioner Secondary / secondary special
## 268 180000 Pensioner Secondary / secondary special
## 269 112500 Pensioner Secondary / secondary special
## 270 166500 Pensioner Secondary / secondary special
## 271 166500 Pensioner Secondary / secondary special
## 272 166500 Pensioner Secondary / secondary special
## 273 90000 Pensioner Higher education
## 274 90000 Pensioner Higher education
## 275 90000 Pensioner Higher education
## 276 90000 Pensioner Higher education
## 277 90000 Pensioner Higher education
## 278 90000 Pensioner Higher education
## 279 103500 Pensioner Secondary / secondary special
## 280 162000 Pensioner Secondary / secondary special
## 281 112500 Pensioner Secondary / secondary special
## 282 112500 Pensioner Secondary / secondary special
## 283 103500 Pensioner Secondary / secondary special
## 284 112500 Pensioner Secondary / secondary special
## 285 162000 Pensioner Secondary / secondary special
## 286 382500 Pensioner Higher education
## 287 135000 Pensioner Secondary / secondary special
## 288 270000 Pensioner Higher education
## 289 144000 Pensioner Higher education
## NAME_FAMILY_STATUS NAME_HOUSING_TYPE DAYS_BIRTH DAYS_EMPLOYED FLAG_MOBIL
## 1 Civil marriage Rented apartment -18682 365243 1
## 2 Civil marriage Rented apartment -18682 365243 1
## 3 Civil marriage Rented apartment -18682 365243 1
## 4 Civil marriage Rented apartment -18682 365243 1
## 5 Civil marriage Rented apartment -18682 365243 1
## 6 Civil marriage Rented apartment -18682 365243 1
## 7 Single / not married Rented apartment -23532 365243 1
## 8 Single / not married Rented apartment -23532 365243 1
## 9 Married Rented apartment -21935 365243 1
## 10 Married Rented apartment -21935 365243 1
## 11 Married Rented apartment -21935 365243 1
## 12 Married Rented apartment -21935 365243 1
## 13 Married Rented apartment -21935 365243 1
## 14 Married Rented apartment -21823 365243 1
## 15 Married Rented apartment -21823 365243 1
## 16 Married Rented apartment -24319 365243 1
## 17 Married Rented apartment -24319 365243 1
## 18 Married Rented apartment -24319 365243 1
## 19 Single / not married Rented apartment -21942 365243 1
## 20 Single / not married Rented apartment -21942 365243 1
## 21 Single / not married Rented apartment -21942 365243 1
## 22 Single / not married Rented apartment -21942 365243 1
## 23 Single / not married Rented apartment -21942 365243 1
## 24 Single / not married Rented apartment -21942 365243 1
## 25 Single / not married Rented apartment -21942 365243 1
## 26 Single / not married Rented apartment -21942 365243 1
## 27 Single / not married Rented apartment -21942 365243 1
## 28 Single / not married Rented apartment -21942 365243 1
## 29 Married Rented apartment -16006 365243 1
## 30 Married Rented apartment -16006 365243 1
## 31 Married Rented apartment -16491 365243 1
## 32 Married Rented apartment -16491 365243 1
## 33 Married Rented apartment -16491 365243 1
## 34 Married Rented apartment -16491 365243 1
## 35 Married Rented apartment -16491 365243 1
## 36 Married Rented apartment -16491 365243 1
## 37 Married Rented apartment -16491 365243 1
## 38 Married Rented apartment -16491 365243 1
## 39 Married Rented apartment -16491 365243 1
## 40 Married Rented apartment -16491 365243 1
## 41 Married Rented apartment -16491 365243 1
## 42 Married Rented apartment -22311 365243 1
## 43 Married Rented apartment -22311 365243 1
## 44 Married Rented apartment -22311 365243 1
## 45 Widow Rented apartment -20833 365243 1
## 46 Widow Rented apartment -20833 365243 1
## 47 Separated Rented apartment -17152 365243 1
## 48 Separated Rented apartment -17152 365243 1
## 49 Separated Rented apartment -20566 365243 1
## 50 Separated Rented apartment -20566 365243 1
## 51 Separated Rented apartment -20566 365243 1
## 52 Separated Rented apartment -20566 365243 1
## 53 Separated Rented apartment -20566 365243 1
## 54 Separated Rented apartment -20566 365243 1
## 55 Separated Rented apartment -20566 365243 1
## 56 Separated Rented apartment -20566 365243 1
## 57 Married Rented apartment -20629 365243 1
## 58 Married Rented apartment -20629 365243 1
## 59 Married Rented apartment -20629 365243 1
## 60 Married Rented apartment -20629 365243 1
## 61 Married Rented apartment -23510 365243 1
## 62 Married Rented apartment -23510 365243 1
## 63 Married Rented apartment -23510 365243 1
## 64 Married Rented apartment -23510 365243 1
## 65 Married Rented apartment -24510 365243 1
## 66 Married Rented apartment -24510 365243 1
## 67 Married Rented apartment -24510 365243 1
## 68 Widow Rented apartment -23716 365243 1
## 69 Widow Rented apartment -23716 365243 1
## 70 Widow Rented apartment -23716 365243 1
## 71 Widow Rented apartment -23716 365243 1
## 72 Widow Rented apartment -23716 365243 1
## 73 Widow Rented apartment -23716 365243 1
## 74 Widow Rented apartment -23716 365243 1
## 75 Widow Rented apartment -23716 365243 1
## 76 Widow Rented apartment -23716 365243 1
## 77 Widow Rented apartment -23716 365243 1
## 78 Widow Rented apartment -23716 365243 1
## 79 Married Rented apartment -23459 365243 1
## 80 Married Rented apartment -23459 365243 1
## 81 Married Rented apartment -23459 365243 1
## 82 Widow Rented apartment -20704 365243 1
## 83 Widow Rented apartment -20704 365243 1
## 84 Widow Rented apartment -20704 365243 1
## 85 Widow Rented apartment -20704 365243 1
## 86 Civil marriage Rented apartment -20884 365243 1
## 87 Married Rented apartment -21123 365243 1
## 88 Married Rented apartment -21123 365243 1
## 89 Married Rented apartment -21123 365243 1
## 90 Married Rented apartment -21123 365243 1
## 91 Married Rented apartment -21123 365243 1
## 92 Married Rented apartment -21123 365243 1
## 93 Married Rented apartment -21123 365243 1
## 94 Married Rented apartment -21123 365243 1
## 95 Married Rented apartment -21123 365243 1
## 96 Married Rented apartment -21123 365243 1
## 97 Married Rented apartment -21123 365243 1
## 98 Married Rented apartment -21123 365243 1
## 99 Married Rented apartment -21123 365243 1
## 100 Married Rented apartment -21123 365243 1
## 101 Single / not married Rented apartment -19635 365243 1
## 102 Married Rented apartment -22540 365243 1
## 103 Widow Rented apartment -20750 365243 1
## 104 Widow Rented apartment -20750 365243 1
## 105 Widow Rented apartment -20750 365243 1
## 106 Widow Rented apartment -20750 365243 1
## 107 Married Rented apartment -20880 365243 1
## 108 Married Rented apartment -20880 365243 1
## 109 Married Rented apartment -20880 365243 1
## 110 Married Rented apartment -20880 365243 1
## 111 Married Rented apartment -20880 365243 1
## 112 Married Rented apartment -20880 365243 1
## 113 Married Rented apartment -10068 365243 1
## 114 Married Rented apartment -10068 365243 1
## 115 Married Rented apartment -10068 365243 1
## 116 Married Rented apartment -10068 365243 1
## 117 Married Rented apartment -10068 365243 1
## 118 Married Rented apartment -20821 365243 1
## 119 Married Rented apartment -20821 365243 1
## 120 Married Rented apartment -20821 365243 1
## 121 Married Rented apartment -23107 365243 1
## 122 Married Rented apartment -23107 365243 1
## 123 Married Rented apartment -23107 365243 1
## 124 Married Rented apartment -21630 365243 1
## 125 Married Rented apartment -21630 365243 1
## 126 Married Rented apartment -21630 365243 1
## 127 Married Rented apartment -16082 365243 1
## 128 Married Rented apartment -16082 365243 1
## 129 Married Rented apartment -16082 365243 1
## 130 Married Rented apartment -16082 365243 1
## 131 Single / not married Rented apartment -20342 365243 1
## 132 Separated Rented apartment -21925 365243 1
## 133 Widow Rented apartment -20234 365243 1
## 134 Widow Rented apartment -20234 365243 1
## 135 Widow Rented apartment -20234 365243 1
## 136 Widow Rented apartment -20234 365243 1
## 137 Widow Rented apartment -20234 365243 1
## 138 Single / not married Rented apartment -24290 365243 1
## 139 Single / not married Rented apartment -24290 365243 1
## 140 Single / not married Rented apartment -24290 365243 1
## 141 Single / not married Rented apartment -24290 365243 1
## 142 Married Rented apartment -20638 365243 1
## 143 Married Rented apartment -20638 365243 1
## 144 Married Rented apartment -22171 365243 1
## 145 Married Rented apartment -22171 365243 1
## 146 Married Rented apartment -22171 365243 1
## 147 Married Rented apartment -22171 365243 1
## 148 Married Rented apartment -22171 365243 1
## 149 Married Rented apartment -23449 365243 1
## 150 Married Rented apartment -23449 365243 1
## 151 Married Rented apartment -23449 365243 1
## 152 Married Rented apartment -23254 365243 1
## 153 Married Rented apartment -23254 365243 1
## 154 Married Rented apartment -23254 365243 1
## 155 Married Rented apartment -23254 365243 1
## 156 Married Rented apartment -23254 365243 1
## 157 Married Rented apartment -23314 365243 1
## 158 Married Rented apartment -23314 365243 1
## 159 Married Rented apartment -23314 365243 1
## 160 Married Rented apartment -23314 365243 1
## 161 Married Rented apartment -23314 365243 1
## 162 Married Rented apartment -23314 365243 1
## 163 Married Rented apartment -23314 365243 1
## 164 Married Rented apartment -23314 365243 1
## 165 Married Rented apartment -23314 365243 1
## 166 Married Rented apartment -23314 365243 1
## 167 Widow Rented apartment -23948 365243 1
## 168 Widow Rented apartment -23948 365243 1
## 169 Widow Rented apartment -23948 365243 1
## 170 Widow Rented apartment -23948 365243 1
## 171 Widow Rented apartment -23948 365243 1
## 172 Widow Rented apartment -23948 365243 1
## 173 Widow Rented apartment -23948 365243 1
## 174 Widow Rented apartment -23948 365243 1
## 175 Widow Rented apartment -23948 365243 1
## 176 Widow Rented apartment -23948 365243 1
## 177 Widow Rented apartment -23948 365243 1
## 178 Widow Rented apartment -23948 365243 1
## 179 Widow Rented apartment -23948 365243 1
## 180 Widow Rented apartment -23948 365243 1
## 181 Widow Rented apartment -23948 365243 1
## 182 Widow Rented apartment -23948 365243 1
## 183 Widow Rented apartment -23948 365243 1
## 184 Widow Rented apartment -23948 365243 1
## 185 Widow Rented apartment -23948 365243 1
## 186 Single / not married Rented apartment -14583 365243 1
## 187 Single / not married Rented apartment -14583 365243 1
## 188 Single / not married Rented apartment -14583 365243 1
## 189 Civil marriage Rented apartment -13835 365243 1
## 190 Civil marriage Rented apartment -13835 365243 1
## 191 Civil marriage Rented apartment -13835 365243 1
## 192 Civil marriage Rented apartment -13835 365243 1
## 193 Civil marriage Rented apartment -13835 365243 1
## 194 Married Rented apartment -22904 365243 1
## 195 Married Rented apartment -22904 365243 1
## 196 Widow Rented apartment -23375 365243 1
## 197 Widow Rented apartment -23375 365243 1
## 198 Widow Rented apartment -23375 365243 1
## 199 Widow Rented apartment -23375 365243 1
## 200 Widow Rented apartment -23375 365243 1
## 201 Widow Rented apartment -23375 365243 1
## 202 Widow Rented apartment -23375 365243 1
## 203 Widow Rented apartment -23375 365243 1
## 204 Widow Rented apartment -23153 365243 1
## 205 Widow Rented apartment -23153 365243 1
## 206 Civil marriage Rented apartment -21319 365243 1
## 207 Single / not married Rented apartment -20132 365243 1
## 208 Single / not married Rented apartment -20132 365243 1
## 209 Single / not married Rented apartment -20132 365243 1
## 210 Single / not married Rented apartment -20132 365243 1
## 211 Single / not married Rented apartment -20132 365243 1
## 212 Single / not married Rented apartment -20132 365243 1
## 213 Single / not married Rented apartment -20132 365243 1
## 214 Single / not married Rented apartment -20132 365243 1
## 215 Single / not married Rented apartment -20132 365243 1
## 216 Single / not married Rented apartment -20132 365243 1
## 217 Single / not married Rented apartment -20132 365243 1
## 218 Single / not married Rented apartment -20132 365243 1
## 219 Single / not married Rented apartment -20132 365243 1
## 220 Single / not married Rented apartment -20132 365243 1
## 221 Single / not married Rented apartment -20132 365243 1
## 222 Single / not married Rented apartment -20132 365243 1
## 223 Single / not married Rented apartment -20132 365243 1
## 224 Single / not married Rented apartment -20132 365243 1
## 225 Single / not married Rented apartment -20132 365243 1
## 226 Married Rented apartment -21878 365243 1
## 227 Married Rented apartment -21878 365243 1
## 228 Married Rented apartment -21878 365243 1
## 229 Married Rented apartment -21878 365243 1
## 230 Married Rented apartment -21878 365243 1
## 231 Married Rented apartment -21878 365243 1
## 232 Married Rented apartment -21878 365243 1
## 233 Married Rented apartment -21878 365243 1
## 234 Married Rented apartment -21878 365243 1
## 235 Married Rented apartment -21878 365243 1
## 236 Married Rented apartment -21878 365243 1
## 237 Married Rented apartment -21878 365243 1
## 238 Married Rented apartment -21878 365243 1
## 239 Married Rented apartment -21878 365243 1
## 240 Married Rented apartment -21878 365243 1
## 241 Married Rented apartment -21878 365243 1
## 242 Married Rented apartment -21878 365243 1
## 243 Married Rented apartment -21878 365243 1
## 244 Married Rented apartment -21878 365243 1
## 245 Married Rented apartment -21878 365243 1
## 246 Married Rented apartment -21878 365243 1
## 247 Married Rented apartment -21878 365243 1
## 248 Married Rented apartment -21878 365243 1
## 249 Married Rented apartment -21878 365243 1
## 250 Married Rented apartment -21878 365243 1
## 251 Married Rented apartment -21878 365243 1
## 252 Married Rented apartment -21878 365243 1
## 253 Married Rented apartment -20300 365243 1
## 254 Married Rented apartment -20300 365243 1
## 255 Married Rented apartment -20300 365243 1
## 256 Single / not married Rented apartment -21162 365243 1
## 257 Single / not married Rented apartment -21162 365243 1
## 258 Married Rented apartment -21229 365243 1
## 259 Married Rented apartment -21229 365243 1
## 260 Married Rented apartment -21229 365243 1
## 261 Married Rented apartment -21229 365243 1
## 262 Married Rented apartment -21229 365243 1
## 263 Married Rented apartment -21229 365243 1
## 264 Married Rented apartment -21229 365243 1
## 265 Married Rented apartment -21229 365243 1
## 266 Married Rented apartment -21229 365243 1
## 267 Married Rented apartment -21229 365243 1
## 268 Civil marriage Rented apartment -17135 365243 1
## 269 Single / not married Rented apartment -12381 365243 1
## 270 Widow Rented apartment -23780 365243 1
## 271 Widow Rented apartment -23780 365243 1
## 272 Widow Rented apartment -23780 365243 1
## 273 Married Rented apartment -15183 365243 1
## 274 Married Rented apartment -15183 365243 1
## 275 Married Rented apartment -15183 365243 1
## 276 Married Rented apartment -15183 365243 1
## 277 Married Rented apartment -15183 365243 1
## 278 Married Rented apartment -15183 365243 1
## 279 Single / not married Rented apartment -20132 365243 1
## 280 Widow Rented apartment -23948 365243 1
## 281 Widow Rented apartment -20704 365243 1
## 282 Married Rented apartment -23107 365243 1
## 283 Single / not married Rented apartment -20132 365243 1
## 284 Married Rented apartment -23107 365243 1
## 285 Widow Rented apartment -23948 365243 1
## 286 Married Rented apartment -10068 365243 1
## 287 Single / not married Rented apartment -10971 -1284 1
## 288 Married Rented apartment -21478 -276 1
## 289 Separated Rented apartment -13691 -293 1
## FLAG_WORK_PHONE FLAG_PHONE FLAG_EMAIL OCCUPATION_TYPE CNT_FAM_MEMBERS
## 1 0 0 0 2
## 2 0 0 0 2
## 3 0 0 0 2
## 4 0 0 0 2
## 5 0 0 0 2
## 6 0 0 0 2
## 7 0 1 0 1
## 8 0 1 0 1
## 9 0 1 0 2
## 10 0 1 0 2
## 11 0 1 0 2
## 12 0 1 0 2
## 13 0 1 0 2
## 14 0 0 0 2
## 15 0 0 0 2
## 16 0 0 0 2
## 17 0 0 0 2
## 18 0 0 0 2
## 19 0 0 0 1
## 20 0 0 0 1
## 21 0 0 0 1
## 22 0 0 0 1
## 23 0 0 0 1
## 24 0 0 0 1
## 25 0 0 0 1
## 26 0 0 0 1
## 27 0 0 0 1
## 28 0 0 0 1
## 29 0 0 0 2
## 30 0 0 0 2
## 31 0 0 0 2
## 32 0 0 0 2
## 33 0 0 0 2
## 34 0 0 0 2
## 35 0 0 0 2
## 36 0 0 0 2
## 37 0 0 0 2
## 38 0 0 0 2
## 39 0 0 0 2
## 40 0 0 0 2
## 41 0 0 0 2
## 42 0 0 0 2
## 43 0 0 0 2
## 44 0 0 0 2
## 45 0 0 0 1
## 46 0 0 0 1
## 47 0 1 1 1
## 48 0 1 1 1
## 49 0 0 0 1
## 50 0 0 0 1
## 51 0 0 0 1
## 52 0 0 0 1
## 53 0 0 0 1
## 54 0 0 0 1
## 55 0 0 0 1
## 56 0 0 0 1
## 57 0 0 0 3
## 58 0 0 0 3
## 59 0 0 0 3
## 60 0 0 0 3
## 61 0 0 0 2
## 62 0 0 0 2
## 63 0 0 0 2
## 64 0 0 0 2
## 65 0 0 0 2
## 66 0 0 0 2
## 67 0 0 0 2
## 68 0 0 0 1
## 69 0 0 0 1
## 70 0 0 0 1
## 71 0 0 0 1
## 72 0 0 0 1
## 73 0 0 0 1
## 74 0 0 0 1
## 75 0 0 0 1
## 76 0 0 0 1
## 77 0 0 0 1
## 78 0 0 0 1
## 79 0 0 0 2
## 80 0 0 0 2
## 81 0 0 0 2
## 82 0 0 0 1
## 83 0 0 0 1
## 84 0 0 0 1
## 85 0 0 0 1
## 86 0 0 0 2
## 87 0 0 1 2
## 88 0 0 1 2
## 89 0 0 1 2
## 90 0 0 1 2
## 91 0 0 1 2
## 92 0 0 1 2
## 93 0 0 1 2
## 94 0 0 1 2
## 95 0 0 1 2
## 96 0 0 1 2
## 97 0 0 1 2
## 98 0 0 1 2
## 99 0 0 1 2
## 100 0 0 1 2
## 101 0 0 0 1
## 102 0 0 0 2
## 103 0 0 1 1
## 104 0 0 1 1
## 105 0 0 1 1
## 106 0 0 1 1
## 107 0 0 0 2
## 108 0 0 0 2
## 109 0 0 0 2
## 110 0 0 0 2
## 111 0 0 0 2
## 112 0 0 0 2
## 113 0 0 0 2
## 114 0 0 0 2
## 115 0 0 0 2
## 116 0 0 0 2
## 117 0 0 0 2
## 118 0 0 0 2
## 119 0 0 0 2
## 120 0 0 0 2
## 121 0 1 0 2
## 122 0 1 0 2
## 123 0 1 0 2
## 124 0 0 0 2
## 125 0 0 0 2
## 126 0 0 0 2
## 127 0 0 0 5
## 128 0 0 0 5
## 129 0 0 0 5
## 130 0 0 0 5
## 131 0 1 1 1
## 132 0 0 0 1
## 133 0 1 0 1
## 134 0 1 0 1
## 135 0 1 0 1
## 136 0 1 0 1
## 137 0 1 0 1
## 138 0 0 0 1
## 139 0 0 0 1
## 140 0 0 0 1
## 141 0 0 0 1
## 142 0 0 0 2
## 143 0 0 0 2
## 144 0 0 0 2
## 145 0 0 0 2
## 146 0 0 0 2
## 147 0 0 0 2
## 148 0 0 0 2
## 149 0 0 0 2
## 150 0 0 0 2
## 151 0 0 0 2
## 152 0 0 0 2
## 153 0 0 0 2
## 154 0 0 0 2
## 155 0 0 0 2
## 156 0 0 0 2
## 157 0 0 0 2
## 158 0 0 0 2
## 159 0 0 0 2
## 160 0 0 0 2
## 161 0 0 0 2
## 162 0 0 0 2
## 163 0 0 0 2
## 164 0 0 0 2
## 165 0 0 0 2
## 166 0 0 0 2
## 167 0 0 0 1
## 168 0 0 0 1
## 169 0 0 0 1
## 170 0 0 0 1
## 171 0 0 0 1
## 172 0 0 0 1
## 173 0 0 0 1
## 174 0 0 0 1
## 175 0 0 0 1
## 176 0 0 0 1
## 177 0 0 0 1
## 178 0 0 0 1
## 179 0 0 0 1
## 180 0 0 0 1
## 181 0 0 0 1
## 182 0 0 0 1
## 183 0 0 0 1
## 184 0 0 0 1
## 185 0 0 0 1
## 186 0 0 0 2
## 187 0 0 0 2
## 188 0 0 0 2
## 189 0 0 0 3
## 190 0 0 0 3
## 191 0 0 0 3
## 192 0 0 0 3
## 193 0 0 0 3
## 194 0 0 0 2
## 195 0 0 0 2
## 196 0 0 0 1
## 197 0 0 0 1
## 198 0 0 0 1
## 199 0 0 0 1
## 200 0 0 0 1
## 201 0 0 0 1
## 202 0 0 0 1
## 203 0 0 0 1
## 204 0 0 0 1
## 205 0 0 0 1
## 206 0 0 0 2
## 207 0 0 0 1
## 208 0 0 0 1
## 209 0 0 0 1
## 210 0 0 0 1
## 211 0 0 0 1
## 212 0 0 0 1
## 213 0 0 0 1
## 214 0 0 0 1
## 215 0 0 0 1
## 216 0 0 0 1
## 217 0 0 0 1
## 218 0 0 0 1
## 219 0 0 0 1
## 220 0 0 0 1
## 221 0 0 0 1
## 222 0 0 0 1
## 223 0 0 0 1
## 224 0 0 0 1
## 225 0 0 0 1
## 226 0 0 0 2
## 227 0 0 0 2
## 228 0 0 0 2
## 229 0 0 0 2
## 230 0 0 0 2
## 231 0 0 0 2
## 232 0 0 0 2
## 233 0 0 0 2
## 234 0 0 0 2
## 235 0 0 0 2
## 236 0 0 0 2
## 237 0 0 0 2
## 238 0 0 0 2
## 239 0 0 0 2
## 240 0 0 0 2
## 241 0 0 0 2
## 242 0 0 0 2
## 243 0 0 0 2
## 244 0 0 0 2
## 245 0 0 0 2
## 246 0 0 0 2
## 247 0 0 0 2
## 248 0 0 0 2
## 249 0 0 0 2
## 250 0 0 0 2
## 251 0 0 0 2
## 252 0 0 0 2
## 253 0 0 0 2
## 254 0 0 0 2
## 255 0 0 0 2
## 256 0 0 0 1
## 257 0 0 0 1
## 258 0 0 0 2
## 259 0 0 0 2
## 260 0 0 0 2
## 261 0 0 0 2
## 262 0 0 0 2
## 263 0 0 0 2
## 264 0 0 0 2
## 265 0 0 0 2
## 266 0 0 0 2
## 267 0 0 0 2
## 268 0 0 0 2
## 269 0 0 0 1
## 270 0 0 0 1
## 271 0 0 0 1
## 272 0 0 0 1
## 273 0 0 0 3
## 274 0 0 0 3
## 275 0 0 0 3
## 276 0 0 0 3
## 277 0 0 0 3
## 278 0 0 0 3
## 279 0 0 0 1
## 280 0 0 0 1
## 281 0 0 0 1
## 282 0 1 0 2
## 283 0 0 0 1
## 284 0 1 0 2
## 285 0 0 0 1
## 286 0 0 0 2
## 287 0 0 0 Managers 1
## 288 0 0 0 Drivers 2
## 289 0 0 0 Laborers 1total_pensioners_rented <- nrow(pensioners_rented)
cat("Total Pensioners in Rented Housing:",total_pensioners_rented)## Total Pensioners in Rented Housing: 289head(pensioners_rented[,c("ID","NAME_INCOME_TYPE", "NAME_HOUSING_TYPE", "AMT_INCOME_TOTAL")])## ID NAME_INCOME_TYPE NAME_HOUSING_TYPE AMT_INCOME_TOTAL
## 1 5009033 Pensioner Rented apartment 255150
## 2 5009034 Pensioner Rented apartment 255150
## 3 5009035 Pensioner Rented apartment 255150
## 4 5009036 Pensioner Rented apartment 255150
## 5 5009037 Pensioner Rented apartment 255150
## 6 5009038 Pensioner Rented apartment 255150- Interpretation: This filter helps in understanding if this group has enough income to cover both rent and potential credit card repayments. Pensioners typically have steady, guaranteed income, but staying in a rented property indicates a lack of permanent housing assets.
Question 2.4: Filter the credit record to isolate high-risk users
who have reached "Status 5" indicating a serious default of
over 150 days.
# Status 5 means critical default
high_risk_defaults <- credit_data %>%
filter(STATUS == '5')
total_high_risk_records <- nrow(high_risk_defaults)
unique_defaulters_count <- length(unique(high_risk_defaults$ID))
cat("Total entries with status 5: ", total_high_risk_records)## Total entries with status 5: 1693cat("\nActual unique customers in default:",unique_defaulters_count)##
## Actual unique customers in default: 195- Interpretation: “Status 5” represents the highest level of payment delay, where an applicant has failed to pay for over 150 days, often leading to a “Written-off” status.we isolate the “Bad” category of our population.
Question 2.5: Calculate the count of applicants who demonstrate professional stability with an employment history of more than 5 years.
# Employment history filtering
# 5 year = 1825 days
stable_employees <- app_data %>%
filter(DAYS_EMPLOYED < (-1825))
total_stable_applicants <- nrow(stable_employees)
cat("Total number of applicants with >5 year of employment:",total_stable_applicants)## Total number of applicants with >5 year of employment: 188948head(stable_employees[,c("ID", "DAYS_EMPLOYED", "NAME_INCOME_TYPE", "AMT_INCOME_TOTAL")])## ID DAYS_EMPLOYED NAME_INCOME_TYPE AMT_INCOME_TOTAL
## 1 5008804 -4542 Working 427500
## 2 5008805 -4542 Working 427500
## 3 5008808 -3051 Commercial associate 270000
## 4 5008809 -3051 Commercial associate 270000
## 5 5008810 -3051 Commercial associate 270000
## 6 5008811 -3051 Commercial associate 270000- Interpretation:The duration of employment is a
primary indicator of financial stability and reliable repayment
behavior:
Applicants in this group are generally considered lower risk because a long tenure at a job suggests a steady income stream and a lower probability of sudden unemployment.
**Detail Report**The initial phases of our analysis successfully established the data’s structural integrity and customer segmentation, starting with the removal of 47 duplicate records to ensure high data quality. Through Level 2 filtering, we identified high-value segments, such as the Top 10 high-income earners and asset-rich applicants (Car/Home owners), while simultaneously isolating
"Status 5"critical defaulters to form the foundation of our risk assessment. Our technical audit revealed a professionally stable applicant pool, with a significant portion possessing over 5 years of experience. By decoding the negative values in theDAYS_EMPLOYEDcolumn as time-offsets from the application date, we have prepared the dataset for accurate feature engineering and predictive credit scoring.
Level 3: Advanced Data Transformation & Insights
Question 3.1: Calculate the average income for each education level while simultaneously engineering a new Age feature (derived from DAYS_BIRTH) to determine how maturity and education interact to influence an applicant’s financial capacity.
app_data <- app_data %>%
mutate(Age=round(abs(DAYS_BIRTH)/365,0))
# Grouping by education and calculating mean Income and Age
edu_profile<-app_data %>%
group_by(NAME_EDUCATION_TYPE) %>%
summarise(
Average_Income = round(mean(AMT_INCOME_TOTAL,na.rm = TRUE),2),
Average_Age = round(mean(Age,na.rm=TRUE),1),
Total_Applicants = n()
) %>%
arrange(desc(Average_Income))
print(edu_profile)## # A tibble: 5 × 4
## NAME_EDUCATION_TYPE Average_Income Average_Age Total_Applicants
## <chr> <dbl> <dbl> <int>
## 1 Academic degree 240692. 44.9 312
## 2 Higher education 226110. 41.5 117512
## 3 Incomplete higher 207330. 35.4 14847
## 4 Secondary / secondary special 172057. 45.1 301788
## 5 Lower secondary 143934. 48.2 4051- Interpretation:The analysis reveals that higher education acts as a financial accelerator, allowing younger applicants (averaging 35–41 years old) to significantly out-earn older applicants (averaging 48 years old) who lack advanced qualifications. This data proves that an applicant’s degree is a better predictor of wealth than their age alone. For credit risk assessment, the bank should prioritize these younger, highly-educated segments as they offer high repayment capacity and a longer potential relationship with the bank.
Question 3.2: Handle the outlier to create a clean Years_of_Experience variable and analyze the volume of applications across different employment types.
outliers_check <- app_data %>%
group_by(NAME_INCOME_TYPE) %>%
summarise(
Min_Days = min(DAYS_EMPLOYED),
Max_Days = max(DAYS_EMPLOYED),
Avg_Days = mean(DAYS_EMPLOYED)
)
cat("Outliers are :","\n")## Outliers are :print(outliers_check)## # A tibble: 5 × 4
## NAME_INCOME_TYPE Min_Days Max_Days Avg_Days
## <chr> <int> <int> <dbl>
## 1 Commercial associate -16495 -12 -2313.
## 2 Pensioner -11662 365243 364443.
## 3 State servant -16767 -16 -3569.
## 4 Student -3904 -382 -2468.
## 5 Working -17531 -12 -2610.- Interpretation:we performed a diagnostic check
which revealed a massive outliers of 365,243 in the
DAYS_EMPLOYEDcolumn, specifically tied to the Pensioner category.this value suggests over 1,000 years of employment which is impossible.
app_data <- app_data %>%
mutate(Years_of_Experience = ifelse(DAYS_EMPLOYED > 0 ,0 ,abs(DAYS_EMPLOYED)/365))
employment_analysis <- app_data %>%
group_by(NAME_INCOME_TYPE) %>%
summarise(
Application_Count = n(),
Average_Years_Experience = round(mean(Years_of_Experience,na.rm = TRUE),1)) %>%
arrange(desc(Application_Count))
print(employment_analysis)## # A tibble: 5 × 3
## NAME_INCOME_TYPE Application_Count Average_Years_Experience
## <chr> <int> <dbl>
## 1 Working 226076 7.2
## 2 Commercial associate 100744 6.3
## 3 Pensioner 75488 0
## 4 State servant 36185 9.8
## 5 Student 17 6.8- Interpretation:we neutralized this anomaly by treating positive values as zero and converting the remaining negative offsets into a readable Years_of_Experience feature. This correction was vital for a realistic analysis.
Question 3.3: Household Per-Capita Financial
Assessment Calculate the median income based on family status
and engineer the Income_per_Member feature to evaluate the
actual disposable income available per person in the household.
app_data <- app_data %>%
mutate(Income_per_Member = AMT_INCOME_TOTAL / CNT_FAM_MEMBERS)
family_financial_summary <- app_data %>%
group_by(NAME_FAMILY_STATUS) %>%
summarise(
Median_Total_Income = median(AMT_INCOME_TOTAL,na.rm = TRUE),
Average_Income_Per_Member = round(mean(Income_per_Member,na.rm=TRUE),2),
Applicant_Count = n()
) %>%
arrange(desc(Average_Income_Per_Member))
print(family_financial_summary)## # A tibble: 5 × 4
## NAME_FAMILY_STATUS Median_Total_Income Average_Income_Per_M…¹ Applicant_Count
## <chr> <dbl> <dbl> <int>
## 1 Single / not marri… 180000 175225. 55258
## 2 Separated 180000 167838. 27251
## 3 Widow 157500 162607. 19674
## 4 Civil marriage 180000 85780. 36529
## 5 Married 157500 79668. 299798
## # ℹ abbreviated name: ¹Average_Income_Per_Member- Interpretation:Single or Separated individuals typically show the highest average income per person, meaning they have more “financial breathing room” compared to Married couples who, despite having higher median total incomes, must divide those resources among more members. For the bank, this “Per-Capita” metric is a superior predictor of repayment capacity, as it identifies applicants who have a higher surplus of cash at the end of the month to service their debt.
Question 3.4: Risk Target Engineering: Implement
the logic to create the binary Is_Bad target column (1 for
high-risk, 0 for healthy) using the credit_record status history to
prepare the data for predictive modeling.
credit_labels <- credit_data %>%
mutate(Is_Bad_Flag = ifelse(STATUS %in% c("1", "2", "3", "4", "5"),1,0)) %>%
group_by(ID) %>%
summarise(Is_Bad = max(Is_Bad_Flag))
summary_table <- table(credit_labels$Is_Bad)
print(summary_table)##
## 0 1
## 40635 5350housing_profile <- app_data %>%
group_by(NAME_HOUSING_TYPE) %>%
summarise(Avg_Age = round(mean(Age, na.rm = TRUE), 1))
print(housing_profile)## # A tibble: 6 × 2
## NAME_HOUSING_TYPE Avg_Age
## <chr> <dbl>
## 1 Co-op apartment 39.3
## 2 House / apartment 44.5
## 3 Municipal apartment 45.5
## 4 Office apartment 40.2
## 5 Rented apartment 37
## 6 With parents 32.6- Interpretation:This step is where we decide who is a “Good” or “Bad” customer. We looked at every customer’s past payments. If someone was even one month late, we marked them as Risky (1). If they always paid on time, they are Safe (0).This “Tag” is the most important part of the project because it tells the bank exactly who they can trust with a credit card.
Question 3.5: Master Dataset Integration: Perform a robust left_join to merge the demographic and credit datasets and generate a final summary of the “Good” vs “Bad” class distribution to check for data imbalance.
# Removing those who don't have a credit record
master_data <- app_data %>%
left_join(credit_labels, by = "ID") %>%
filter(!is.na(Is_Bad))
# This tells us if our data is 'Imbalanced' (more Good than Bad)
final_summary <- master_data %>%
group_by(Is_Bad) %>%
summarise(
Total_Count = n(),
Percentage = round((n() / nrow(master_data)) * 100, 2)
)
print(final_summary)## # A tibble: 2 × 3
## Is_Bad Total_Count Percentage
## <dbl> <int> <dbl>
## 1 0 32166 88.2
## 2 1 4291 11.8- Interpretation:This is the final step where we put all the pieces of the puzzle together. We have joined our two separate files into one Master Dataset. Now, for every person, we can see their Age, Income, and Education right next to their “Good” or “Bad” tag.It is also know as Class Imbalance.
print(colnames(master_data))## [1] "ID" "CODE_GENDER" "FLAG_OWN_CAR"
## [4] "FLAG_OWN_REALTY" "CNT_CHILDREN" "AMT_INCOME_TOTAL"
## [7] "NAME_INCOME_TYPE" "NAME_EDUCATION_TYPE" "NAME_FAMILY_STATUS"
## [10] "NAME_HOUSING_TYPE" "DAYS_BIRTH" "DAYS_EMPLOYED"
## [13] "FLAG_MOBIL" "FLAG_WORK_PHONE" "FLAG_PHONE"
## [16] "FLAG_EMAIL" "OCCUPATION_TYPE" "CNT_FAM_MEMBERS"
## [19] "Age" "Years_of_Experience" "Income_per_Member"
## [22] "Is_Bad"head(master_data)## ID CODE_GENDER FLAG_OWN_CAR FLAG_OWN_REALTY CNT_CHILDREN
## 1 5008804 M Y Y 0
## 2 5008805 M Y Y 0
## 3 5008806 M Y Y 0
## 4 5008808 F N Y 0
## 5 5008809 F N Y 0
## 6 5008810 F N Y 0
## AMT_INCOME_TOTAL NAME_INCOME_TYPE NAME_EDUCATION_TYPE
## 1 427500 Working Higher education
## 2 427500 Working Higher education
## 3 112500 Working Secondary / secondary special
## 4 270000 Commercial associate Secondary / secondary special
## 5 270000 Commercial associate Secondary / secondary special
## 6 270000 Commercial associate Secondary / secondary special
## NAME_FAMILY_STATUS NAME_HOUSING_TYPE DAYS_BIRTH DAYS_EMPLOYED FLAG_MOBIL
## 1 Civil marriage Rented apartment -12005 -4542 1
## 2 Civil marriage Rented apartment -12005 -4542 1
## 3 Married House / apartment -21474 -1134 1
## 4 Single / not married House / apartment -19110 -3051 1
## 5 Single / not married House / apartment -19110 -3051 1
## 6 Single / not married House / apartment -19110 -3051 1
## FLAG_WORK_PHONE FLAG_PHONE FLAG_EMAIL OCCUPATION_TYPE CNT_FAM_MEMBERS Age
## 1 1 0 0 2 33
## 2 1 0 0 2 33
## 3 0 0 0 Security staff 2 59
## 4 0 1 1 Sales staff 1 52
## 5 0 1 1 Sales staff 1 52
## 6 0 1 1 Sales staff 1 52
## Years_of_Experience Income_per_Member Is_Bad
## 1 12.443836 213750 1
## 2 12.443836 213750 1
## 3 3.106849 56250 0
## 4 8.358904 270000 0
## 5 8.358904 270000 0
## 6 8.358904 270000 0Level 4: Exploratory Data Analysis (EDA)
Question 4.1: Target Class Frequency Analysis:
- Task: Generate a frequency bar chart to visualize
the distribution of the
Is_Badtarget variable. This analysis is essential to identify Class Imbalance, which determines the baseline accuracy required for future predictive modeling. - Objective: To determine the ratio of healthy (0) vs. risky (1) accounts in the master dataset.
ggplot(master_data, aes(x = as.factor(Is_Bad), fill = as.factor(Is_Bad))) +
geom_bar(color = "black", width = 0.6) +
# Adding count labels on top of bars
geom_text(stat='count', aes(label=..count..), vjust=-0.3, size=4) +
scale_fill_manual(values = c("0" = "skyblue", "1" = "orange"),
labels = c("Healthy (0)", "Risky (1)")) +
labs(title = "Visualizing Class Imbalance in Applicant Data",
x = "Credit Category (0 = Good, 1 = Bad)",
y = "Number of Applicants",
fill = "Legend") +
theme_minimal()## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
- Interpretation:we can observe a clear Class Imbalance. The number of healthy customers significantly outweights the number of risky ones. In Data Science, identifying this imbalance is crucial because it tells us that our future predictive model might become biased.This visualization helps us decide that we need better evaluation metrics (like Precision and Recall) instead of just relying on overall accuracy.
Question 4.2: Demographic Age Distribution and Skewness:
- Task: Construct a histogram to analyze the age distribution of the applicant pool using the engineered Age feature. Apply a density overlay to observe the data spread and identify the peak age group for credit applications.
- Objective: To understand the life-stage and maturity profile of the primary customer base.
# Creating the Age Histogram with KDE Curve
ggplot(master_data, aes(x = Age)) +
geom_histogram(aes(y = ..density..), binwidth = 2, fill = "lightgreen", color = "white") +
geom_density(alpha = 0.3, color = "red") +
# Reference line for Average Age
geom_vline(aes(xintercept = mean(Age)), color = "black", linetype = "dashed", size = 1) +
labs(title = "Applicant Age Distribution",
subtitle = "Identifying the Peak Age Group for Credit Seeking",
x = "Age (Years)",
y = "Density",
caption = "Black line represents the Average Age") +
theme_classic()## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
- Interpretation:By combining a histogram with a KDE (Density) curve, we can observe that the majority of credit seekers fall within the 30 to 50 age bracket.From a risk perspective, this is a very positive sign for the bank. Applicants aged 40-50 are traditionally considered low-risk because of job stability and financial experience.This maturity translates to lower credit risk, as they have a more disciplined approach to debt repayment.
Question 4.3: Financial Variance & Outliers Detection:
Task: Create a categorical boxplot comparing
AMT_INCOME_TOTAL across different
NAME_HOUSING_TYPE categories. Utilize a log-scale to
normalize high-income variations and identify significant financial
outliers. Objective: To investigate the relationship
between housing stability and income levels.
# 3. Boxplot: Income vs Housing Type
ggplot(master_data, aes(x = NAME_HOUSING_TYPE, y = AMT_INCOME_TOTAL, fill = NAME_HOUSING_TYPE)) +
geom_boxplot(outlier.color = "red", outlier.shape = 16, outlier.size = 2) +
# Using Log scale to normalize the huge income gaps
scale_y_log10() +
# Using simple, distinct color names for clarity
scale_fill_manual(values = c("House / apartment" = "skyblue",
"With parents" = "gold",
"Municipal apartment" = "lightpink",
"Rented apartment" = "lightgreen",
"Office apartment" = "orange",
"Co-op apartment" = "plum")) +
labs(title = "Income Distribution by Housing Type",
subtitle = "Comparing Financial Strength across Living Situations",
x = "Housing Category",
y = "Total Income (Log Scale)") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1), # Rotating names for neatness
legend.position = "none") # Removing legend since X-axis labels are enough