Final Presentation: Fraud Simulation Data

Quarto

Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see https://quarto.org.

Running Code

When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:

1 + 1

[1] 2

You can add options to executable code like this

[1] 4

The echo: false option disables the printing of code (only output is displayed).

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.1     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.3     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tidyr)
library(viridis)

Loading required package: viridisLite

library(dplyr)

fraud_detect<- read_csv("healthcare_fraud_detection-selected-columns-2.csv")

Rows: 10000 Columns: 12
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr  (6): Provider_ID, Claim_ID, Patient_Gender, Diagnosis_Code, Insurance_T...
dbl  (5): Patient_Age, Procedure_Code, Claim_Amount, Approved_Amount, Is_Fraud
date (1): Claim_Submission_Date

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(fraud_detect)

# A tibble: 6 × 12
  Provider_ID Claim_ID Patient_Age Patient_Gender Diagnosis_Code Procedure_Code
  <chr>       <chr>          <dbl> <chr>          <chr>                   <dbl>
1 P0052       C0000000          37 Male           I25.10                  36415
2 P0121       C0000001          21 Female         E11.9                   99213
3 P0140       C0000002          78 Female         J06.9                   93000
4 P0202       C0000003          65 Male           I10                     93000
5 P0135       C0000004          36 Male           M54.5                   85025
6 P0241       C0000005          44 Female         E11.9                   80053
# ℹ 6 more variables: Claim_Amount <dbl>, Approved_Amount <dbl>,
#   Insurance_Type <chr>, Claim_Submission_Date <date>, Patient_State <chr>,
#   Is_Fraud <dbl>

nrow(fraud_detect)

[1] 10000

min(fraud_detect$Approved_Amount)

[1] 50.35

max(fraud_detect$Approved_Amount)

[1] 4270.89

min(fraud_detect$Claim_Amount)

[1] 60.21

max(fraud_detect$Claim_Amount)

[1] 6590.7

PublicIns <- fraud_detect |>
  filter(
    Patient_State == "IL",
    Approved_Amount >= 100,
    Approved_Amount <= 500) |>
  arrange(Claim_Submission_Date)

ggplot(fraud_detect, aes(x=Claim_Amount, y=Approved_Amount)) +
  geom_point()

ggplot(data = fraud_detect) + 
  stat_summary(
    mapping = aes(x = Claim_Amount, y = Approved_Amount),
    fun.min = min,
    fun.max = max,
    fun = median
  )

p1 <- fraud_detect |>
  ggplot(aes(x=Claim_Amount, fill=Insurance_Type)) +
  geom_histogram(position="identity")+
  scale_fill_discrete(name = "Insurance_Type", 
                      labels = c("Self-Pay", "Medicaid","Medicare", "Private")) +
  labs(x = "Claim Amounts", 
       y = "Frequency of Claims",
       title = "Histogram of Claim Amounts",
       caption = "Fraud Simulation")
p1

`stat_bin()` using `bins = 30`. Pick better value `binwidth`.

p2 <- fraud_detect |>
  ggplot(aes(Insurance_Type, Claim_Amount, fill = Insurance_Type)) + 
  labs(x = "Insurance Type", y = "Claim Amount", 
       title = "Side-by-Side Boxplot of Claim Amount",
       caption = "Kaggle Fraud Simulation Data") +
  geom_boxplot()+
  scale_fill_grey(name = "Insurance_Type", 
                  labels = c("Self-Pay", "Medicaid","Medicare", "Private"))
p2

ggplot(data = fraud_detect) + 
  geom_bar(aes(x = Insurance_Type, fill = Patient_Gender), position = "stack") +
  labs(x = "Insurance Type", y = "Frequency", 
       title = "Stacked Bar Graph of Insurance Type by Gender")

ggplot(data = PublicIns) + 
  geom_bar(aes(x = Insurance_Type, fill = Patient_Gender), position = "stack") +
  labs(x = "Insurance Type", y = "Frequency", 
       title = "Stacked Bar Graph of Insurance Type by Gender in Illinois")

p5 <- PublicIns |>
  ggplot(aes(Insurance_Type, Claim_Amount, fill = Insurance_Type)) + 
  labs(x = "Insurance Type", y = "Claim Amount", 
       title = "Side-by-Side Boxplot of Claim Amount",
       caption = "Kaggle Fraud Simulation Data") +
  geom_boxplot()+
  scale_fill_grey(name = "Insurance_Type", 
                  labels = c("Self-Pay", "Medicaid","Medicare", "Private"))
p5