library(readxl)
Telco <- read_excel("C:/Users/DELL/Desktop/DA/Data.xlsx",
sheet = "Main")
View(Telco)
library(ggplot2)
library(ggpie)
library(dplyr)
library(tidyverse)
library(corrplot)
library(lmtest)
library(patchwork)
library(caTools)
library(sjPlot)
library(car)
library(caret)
library(stargazer)
library(rpart)
library(rpart.plot)
Telecom customer churn is a dataset that contains information about customers of a telecommunications company and whether they have churned (i.e., stopped using the company’s services) or stayed. Main services include: Phone service and Internet service
| Variables | Data type |
|---|---|
| Gender | Qualitative data |
| Age group | Qualitative data |
| Married | Qualitative data |
| Number of Dependents | Quantitative data |
| Number of Referrals | Quantitative data |
| Tenure in Months | Quantitative data |
| Offer | Qualitative data |
| Phone Service | Qualitative data |
| Avg Monthly Long Distance Charges | Quantitative data |
| Multiple Lines | Quantitative data |
| Internet Service | Qualitative data |
| Internet Type | Qualitative data |
| Avg Monthly GB Download | Quantitative data |
| Online Security | Qualitative data |
| Online Backup | Qualitative data |
| Device Protection Plan | Qualitative data |
| Premium Tech Support | Qualitative data |
| Streaming TV | Qualitative data |
| Streaming Movies | Qualitative data |
| Streaming Music | Qualitative data |
| Unlimited Data | Qualitative data |
| Contract | Qualitative data |
| Paperless Billing | Qualitative data |
| Payment Method | Qualitative data |
| Monthly Charge | Quantitative data |
| Total Charges | Quantitative data |
| Total Refunds | Quantitative data |
| Total Extra Data Charges | Quantitative data |
| Total Long Distance Charges | Quantitative data |
| Total Revenue | Quantitative data |
| Customer Status | Qualitative data |
sum(duplicated(Telco))
## [1] 0
Telco dataset with no duplicate values refers to a collection of data where each entry is unique, and there are no repetitions or duplicates within the dataset.
sapply(Telco, function(x) sum(is.na(x)))
## Gender Cus ID
## 0 0
## Age Age Group
## 0 0
## Married Number of Dependents
## 0 0
## Number of Referrals Tenure in Months
## 0 0
## Offer Phone Service
## 0 0
## Avg Monthly Long Distance Charges Multiple Lines
## 682 682
## Internet Service Internet Type
## 0 1526
## Avg Monthly GB Download Online Security
## 1526 1526
## Online Backup Device Protection Plan
## 1526 1526
## Premium Tech Support Streaming TV
## 1526 1526
## Streaming Movies Streaming Music
## 1526 1526
## Unlimited Data Contract
## 1526 0
## Paperless Billing Payment Method
## 0 0
## Monthly Charge Total Charges
## 0 0
## Total Refunds Total Extra Data Charges
## 0 0
## Total Long Distance Charges Total Revenue
## 0 0
## Customer Status
## 0
In the dataset, there are 682 responses where respondents indicated “No” for Phone service and 1526 responses where they indicated “No” for Internet service, resulting in missing values for both dimensions. This substantial number of missing values underscores a significant portion of the population that does not use phone or Internet services.
Thus, author decides to use only observations that do not have missing values of Phone service in Telco dataset
telco_use_phone = Telco[complete.cases(Telco$`Multiple Lines`), -c(13:23)]
#Churn
telco_use_phone$Churn = case_when(
telco_use_phone$`Customer Status`== "Churned" ~ "Yes",
TRUE ~ "No")
summary(telco_use_phone)
## Gender Cus ID Age Age Group
## Length:6361 Length:6361 Min. :19.00 Length:6361
## Class :character Class :character 1st Qu.:32.00 Class :character
## Mode :character Mode :character Median :46.00 Mode :character
## Mean :46.56
## 3rd Qu.:60.00
## Max. :80.00
## Married Number of Dependents Number of Referrals Tenure in Months
## Length:6361 Min. :0.0000 Min. : 0.000 Min. : 1.00
## Class :character 1st Qu.:0.0000 1st Qu.: 0.000 1st Qu.: 9.00
## Mode :character Median :0.0000 Median : 0.000 Median :29.00
## Mean :0.4655 Mean : 1.962 Mean :32.45
## 3rd Qu.:0.0000 3rd Qu.: 3.000 3rd Qu.:56.00
## Max. :8.0000 Max. :11.000 Max. :72.00
## Offer Phone Service Avg Monthly Long Distance Charges
## Length:6361 Length:6361 Min. : 1.01
## Class :character Class :character 1st Qu.:13.05
## Mode :character Mode :character Median :25.69
## Mean :25.42
## 3rd Qu.:37.68
## Max. :49.99
## Multiple Lines Contract Paperless Billing Payment Method
## Length:6361 Length:6361 Length:6361 Length:6361
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Monthly Charge Total Charges Total Refunds Total Extra Data Charges
## Min. :-10.00 Min. : 18.8 Min. : 0.000 Min. : 0.000
## 1st Qu.: 26.10 1st Qu.: 414.1 1st Qu.: 0.000 1st Qu.: 0.000
## Median : 74.40 Median :1417.9 Median : 0.000 Median : 0.000
## Mean : 65.99 Mean :2364.3 Mean : 1.979 Mean : 6.609
## 3rd Qu.: 91.00 3rd Qu.:4024.2 3rd Qu.: 0.000 3rd Qu.: 0.000
## Max. :118.75 Max. :8684.8 Max. :49.790 Max. :150.000
## Total Long Distance Charges Total Revenue Customer Status
## Min. : 1.13 Min. : 21.36 Length:6361
## 1st Qu.: 133.40 1st Qu.: 671.88 Class :character
## Median : 509.21 Median : 2284.19 Mode :character
## Mean : 829.41 Mean : 3198.35
## 3rd Qu.:1320.57 3rd Qu.: 5248.80
## Max. :3564.72 Max. :11979.34
## Churn
## Length:6361
## Class :character
## Mode :character
##
##
##
sapply(telco_use_phone, function(x) sd(x))
## Gender Cus ID
## NA NA
## Age Age Group
## 16.7364133 NA
## Married Number of Dependents
## NA 0.9541926
## Number of Referrals Tenure in Months
## 3.0033168 24.5793233
## Offer Phone Service
## NA NA
## Avg Monthly Long Distance Charges Multiple Lines
## 14.2003736 NA
## Contract Paperless Billing
## NA NA
## Payment Method Monthly Charge
## NA 31.6452802
## Total Charges Total Refunds
## 2328.3895348 7.9318419
## Total Extra Data Charges Total Long Distance Charges
## 24.7431988 852.6875468
## Total Revenue Customer Status
## 2935.8093142 NA
## Churn
## NA
telco_use_phone = subset(telco_use_phone,`Monthly Charge` > 1)
To ensure accuracy in analyses, author removes rows with negative values in the Monthly Charge because negative values in this variable may indicate errors in billing data, which could be wrong statistical analyses and interpretations from the dataset.
by(telco_use_phone$`Total Revenue`,telco_use_phone$Offer,summary)
## telco_use_phone$Offer: None
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 21.4 626.1 2219.5 3088.4 4877.6 11688.9
## ------------------------------------------------------------
## telco_use_phone$Offer: Offer A
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1579 5941 7783 7345 9167 11979
## ------------------------------------------------------------
## telco_use_phone$Offer: Offer B
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 820.9 3870.9 5492.9 5357.1 6789.2 10184.5
## ------------------------------------------------------------
## telco_use_phone$Offer: Offer C
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 454.1 2197.3 2971.3 2940.6 3804.3 6027.6
## ------------------------------------------------------------
## telco_use_phone$Offer: Offer D
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 212.8 895.3 1305.2 1373.0 1817.0 3273.1
## ------------------------------------------------------------
## telco_use_phone$Offer: Offer E
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 21.36 99.17 222.60 323.40 467.51 1351.16
by(telco_use_phone$`Total Revenue`,telco_use_phone$Contract,summary)
## telco_use_phone$Contract: Month-to-Month
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 21.36 237.17 965.13 1813.78 2669.70 10718.96
## ------------------------------------------------------------
## telco_use_phone$Contract: One Year
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 43.06 1796.75 3893.90 4234.19 6533.20 11355.87
## ------------------------------------------------------------
## telco_use_phone$Contract: Two Year
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 50.44 2263.29 4690.34 5016.92 7700.41 11979.34
\[ p=P(y=1)=\frac{\epsilon^{\beta_1 + \beta_2*X_2 + ... + \beta_n*X_n}}{1+\epsilon^{\beta_1 + \beta_2*X_2 + ... + \beta_n*X_n}} \]
\[ ln(\frac{p}{1-p}) = \beta_1 + \beta_2*X_2 + \beta_3*X_3 + ... + \beta_n*X_n \]
When \(X_j\) changes 1 unit => odd ratio \(\frac{p}{1-p}\) changes \(\epsilon^{\beta_j}\) times
telco_use_phone = mutate(telco_use_phone,
Churn = ifelse(Churn == "Yes", 1, 0))
telco_use_phone$Churn_text = ifelse(telco_use_phone$Churn == 0,
"Stayed","Churned")
set.seed(2610)
split = sample.split(telco_use_phone$Churn,SplitRatio = 0.8)
train = subset(telco_use_phone, split == TRUE)
test = subset(telco_use_phone, split == FALSE)
train1 = train[,c(1,4:9,11:16,21,23)]
train2 = train[,c(1,4:9,11:16,21,24)]
test1 = test[,c(1,4:9,11:16,21,23)]
test2 = test[,c(1,4:9,11:16,21,24)]
md = glm(Churn ~ . , data = train1, family = "binomial")
md1 =glm(Churn ~. -Offer, data = train1, family = "binomial")
md2 =glm(Churn ~. -Offer - `Avg Monthly Long Distance Charges`, data = train1, family = "binomial")
summary(md)
##
## Call:
## glm(formula = Churn ~ ., family = "binomial", data = train1)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.635e+00 2.458e-01 -6.651 2.91e-11 ***
## GenderMale -2.643e-02 8.391e-02 -0.315 0.752761
## `Age Group`30 - 59 1.350e-01 1.134e-01 1.191 0.233808
## `Age Group`60 - 89 4.901e-01 1.282e-01 3.824 0.000132 ***
## MarriedYes 1.542e+00 1.271e-01 12.131 < 2e-16 ***
## `Number of Dependents` -6.239e-01 7.286e-02 -8.563 < 2e-16 ***
## `Number of Referrals` -5.228e-01 3.904e-02 -13.391 < 2e-16 ***
## `Tenure in Months` -4.823e-02 9.490e-03 -5.082 3.74e-07 ***
## OfferOffer A 6.082e-01 2.878e-01 2.113 0.034581 *
## OfferOffer B -1.997e-01 1.839e-01 -1.086 0.277489
## OfferOffer C -1.722e-01 1.809e-01 -0.952 0.341125
## OfferOffer D -5.030e-01 1.455e-01 -3.458 0.000544 ***
## OfferOffer E 3.870e-01 1.272e-01 3.042 0.002352 **
## `Avg Monthly Long Distance Charges` -2.657e-03 3.428e-03 -0.775 0.438231
## `Multiple Lines`Yes 2.041e-01 1.002e-01 2.037 0.041610 *
## ContractOne Year -1.426e+00 1.329e-01 -10.729 < 2e-16 ***
## ContractTwo Year -2.699e+00 2.120e-01 -12.729 < 2e-16 ***
## `Paperless Billing`Yes 3.019e-01 9.611e-02 3.141 0.001682 **
## `Payment Method`Credit Card -4.275e-01 9.737e-02 -4.390 1.13e-05 ***
## `Payment Method`Mailed Check 4.705e-01 1.802e-01 2.611 0.009025 **
## `Monthly Charge` 2.583e-02 2.532e-03 10.202 < 2e-16 ***
## `Total Revenue` 1.564e-04 7.896e-05 1.981 0.047572 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 5809.2 on 5000 degrees of freedom
## Residual deviance: 3519.5 on 4979 degrees of freedom
## AIC: 3563.5
##
## Number of Fisher Scoring iterations: 7
summary(md1)
##
## Call:
## glm(formula = Churn ~ . - Offer, family = "binomial", data = train1)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.371e+00 2.349e-01 -5.836 5.35e-09 ***
## GenderMale -4.149e-02 8.325e-02 -0.498 0.618224
## `Age Group`30 - 59 1.229e-01 1.125e-01 1.093 0.274428
## `Age Group`60 - 89 4.826e-01 1.271e-01 3.797 0.000146 ***
## MarriedYes 1.549e+00 1.271e-01 12.186 < 2e-16 ***
## `Number of Dependents` -6.289e-01 7.252e-02 -8.672 < 2e-16 ***
## `Number of Referrals` -5.261e-01 3.907e-02 -13.466 < 2e-16 ***
## `Tenure in Months` -6.158e-02 9.368e-03 -6.573 4.93e-11 ***
## `Avg Monthly Long Distance Charges` -4.555e-03 3.381e-03 -1.347 0.177929
## `Multiple Lines`Yes 1.716e-01 9.885e-02 1.736 0.082477 .
## ContractOne Year -1.416e+00 1.318e-01 -10.743 < 2e-16 ***
## ContractTwo Year -2.517e+00 2.017e-01 -12.479 < 2e-16 ***
## `Paperless Billing`Yes 3.079e-01 9.549e-02 3.225 0.001261 **
## `Payment Method`Credit Card -4.346e-01 9.685e-02 -4.488 7.20e-06 ***
## `Payment Method`Mailed Check 4.576e-01 1.777e-01 2.576 0.009996 **
## `Monthly Charge` 2.375e-02 2.466e-03 9.629 < 2e-16 ***
## `Total Revenue` 2.585e-04 7.801e-05 3.314 0.000921 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 5809.2 on 5000 degrees of freedom
## Residual deviance: 3554.0 on 4984 degrees of freedom
## AIC: 3588
##
## Number of Fisher Scoring iterations: 7
summary(md2)
##
## Call:
## glm(formula = Churn ~ . - Offer - `Avg Monthly Long Distance Charges`,
## family = "binomial", data = train1)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.542e+00 1.985e-01 -7.770 7.86e-15 ***
## GenderMale -4.144e-02 8.326e-02 -0.498 0.618708
## `Age Group`30 - 59 1.279e-01 1.124e-01 1.138 0.255070
## `Age Group`60 - 89 4.853e-01 1.271e-01 3.818 0.000135 ***
## MarriedYes 1.553e+00 1.270e-01 12.223 < 2e-16 ***
## `Number of Dependents` -6.281e-01 7.248e-02 -8.666 < 2e-16 ***
## `Number of Referrals` -5.270e-01 3.903e-02 -13.502 < 2e-16 ***
## `Tenure in Months` -5.577e-02 8.258e-03 -6.754 1.44e-11 ***
## `Multiple Lines`Yes 1.748e-01 9.875e-02 1.770 0.076758 .
## ContractOne Year -1.416e+00 1.315e-01 -10.766 < 2e-16 ***
## ContractTwo Year -2.503e+00 2.009e-01 -12.459 < 2e-16 ***
## `Paperless Billing`Yes 3.084e-01 9.545e-02 3.231 0.001234 **
## `Payment Method`Credit Card -4.338e-01 9.682e-02 -4.480 7.46e-06 ***
## `Payment Method`Mailed Check 4.627e-01 1.775e-01 2.606 0.009151 **
## `Monthly Charge` 2.443e-02 2.421e-03 10.088 < 2e-16 ***
## `Total Revenue` 2.063e-04 6.741e-05 3.060 0.002212 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 5809.2 on 5000 degrees of freedom
## Residual deviance: 3555.8 on 4985 degrees of freedom
## AIC: 3587.8
##
## Number of Fisher Scoring iterations: 7
##
## ====================================================================
## Dependent variable:
## --------------------------------
## Churn
## (1) (2) (3)
## --------------------------------------------------------------------
## GenderMale -0.026 -0.041 -0.041
## (0.084) (0.083) (0.083)
##
## `Age Group`30 - 59 0.135 0.123 0.128
## (0.113) (0.112) (0.112)
##
## `Age Group`60 - 89 0.490*** 0.483*** 0.485***
## (0.128) (0.127) (0.127)
##
## MarriedYes 1.542*** 1.549*** 1.553***
## (0.127) (0.127) (0.127)
##
## `Number of Dependents` -0.624*** -0.629*** -0.628***
## (0.073) (0.073) (0.072)
##
## `Number of Referrals` -0.523*** -0.526*** -0.527***
## (0.039) (0.039) (0.039)
##
## `Tenure in Months` -0.048*** -0.062*** -0.056***
## (0.009) (0.009) (0.008)
##
## OfferOffer A 0.608**
## (0.288)
##
## OfferOffer B -0.200
## (0.184)
##
## OfferOffer C -0.172
## (0.181)
##
## OfferOffer D -0.503***
## (0.145)
##
## OfferOffer E 0.387***
## (0.127)
##
## `Avg Monthly Long Distance Charges` -0.003 -0.005
## (0.003) (0.003)
##
## `Multiple Lines`Yes 0.204** 0.172* 0.175*
## (0.100) (0.099) (0.099)
##
## ContractOne Year -1.426*** -1.416*** -1.416***
## (0.133) (0.132) (0.132)
##
## ContractTwo Year -2.699*** -2.517*** -2.503***
## (0.212) (0.202) (0.201)
##
## `Paperless Billing`Yes 0.302*** 0.308*** 0.308***
## (0.096) (0.095) (0.095)
##
## `Payment Method`Credit Card -0.428*** -0.435*** -0.434***
## (0.097) (0.097) (0.097)
##
## `Payment Method`Mailed Check 0.470*** 0.458*** 0.463***
## (0.180) (0.178) (0.178)
##
## `Monthly Charge` 0.026*** 0.024*** 0.024***
## (0.003) (0.002) (0.002)
##
## `Total Revenue` 0.0002** 0.0003*** 0.0002***
## (0.0001) (0.0001) (0.0001)
##
## Constant -1.635*** -1.371*** -1.542***
## (0.246) (0.235) (0.198)
##
## --------------------------------------------------------------------
## Observations 5,001 5,001 5,001
## Log Likelihood -1,759.768 -1,776.990 -1,777.898
## Akaike Inf. Crit. 3,563.537 3,587.980 3,587.795
## ====================================================================
## Note: *p<0.1; **p<0.05; ***p<0.01
anova(md,md1,test = "LR")
## Analysis of Deviance Table
##
## Model 1: Churn ~ Gender + `Age Group` + Married + `Number of Dependents` +
## `Number of Referrals` + `Tenure in Months` + Offer + `Avg Monthly Long Distance Charges` +
## `Multiple Lines` + Contract + `Paperless Billing` + `Payment Method` +
## `Monthly Charge` + `Total Revenue`
## Model 2: Churn ~ (Gender + `Age Group` + Married + `Number of Dependents` +
## `Number of Referrals` + `Tenure in Months` + Offer + `Avg Monthly Long Distance Charges` +
## `Multiple Lines` + Contract + `Paperless Billing` + `Payment Method` +
## `Monthly Charge` + `Total Revenue`) - Offer
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 4979 3519.5
## 2 4984 3554.0 -5 -34.443 1.943e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
anova(md1,md2,test = "LR")
## Analysis of Deviance Table
##
## Model 1: Churn ~ (Gender + `Age Group` + Married + `Number of Dependents` +
## `Number of Referrals` + `Tenure in Months` + Offer + `Avg Monthly Long Distance Charges` +
## `Multiple Lines` + Contract + `Paperless Billing` + `Payment Method` +
## `Monthly Charge` + `Total Revenue`) - Offer
## Model 2: Churn ~ (Gender + `Age Group` + Married + `Number of Dependents` +
## `Number of Referrals` + `Tenure in Months` + Offer + `Avg Monthly Long Distance Charges` +
## `Multiple Lines` + Contract + `Paperless Billing` + `Payment Method` +
## `Monthly Charge` + `Total Revenue`) - Offer - `Avg Monthly Long Distance Charges`
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 4984 3554.0
## 2 4985 3555.8 -1 -1.815 0.1779
=> Choose model 1
exp(coef(md1))
## (Intercept) GenderMale
## 0.2539304 0.9593585
## `Age Group`30 - 59 `Age Group`60 - 89
## 1.1307787 1.6203157
## MarriedYes `Number of Dependents`
## 4.7045677 0.5331835
## `Number of Referrals` `Tenure in Months`
## 0.5909016 0.9402811
## `Avg Monthly Long Distance Charges` `Multiple Lines`Yes
## 0.9954556 1.1872621
## ContractOne Year ContractTwo Year
## 0.2426864 0.0807266
## `Paperless Billing`Yes `Payment Method`Credit Card
## 1.3606103 0.6475098
## `Payment Method`Mailed Check `Monthly Charge`
## 1.5803468 1.0240335
## `Total Revenue`
## 1.0002585
pr1 = predict(md1, test1, type = "response")
predicted = round(pr1)
tbl1 = table(Prediction = predicted, Actual = test1$Churn)
confusionMatrix(tbl1, positive = "1", mode = "everything")
## Confusion Matrix and Statistics
##
## Actual
## Prediction 0 1
## 0 828 111
## 1 88 224
##
## Accuracy : 0.8409
## 95% CI : (0.8195, 0.8608)
## No Information Rate : 0.7322
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.5853
##
## Mcnemar's Test P-Value : 0.1189
##
## Sensitivity : 0.6687
## Specificity : 0.9039
## Pos Pred Value : 0.7179
## Neg Pred Value : 0.8818
## Precision : 0.7179
## Recall : 0.6687
## F1 : 0.6924
## Prevalence : 0.2678
## Detection Rate : 0.1791
## Detection Prevalence : 0.2494
## Balanced Accuracy : 0.7863
##
## 'Positive' Class : 1
##
dtr = rpart(Churn_text ~ ., data = train2, method = "class")
Initially, probability of stay decision is 0.73, first sample size divides into 51% and 49%. In layer 2, probability of stay decision is 0.54, 51% out of first sample size continues to divide into 32% and 19%.
pr2 = predict(dtr, test2, type = "class")
tbl2= table(Prediction = pr2, Actual = test2$Churn_text)
confusionMatrix(tbl2, positive = "Churned", mode = "everything")
## Confusion Matrix and Statistics
##
## Actual
## Prediction Churned Stayed
## Churned 178 48
## Stayed 157 868
##
## Accuracy : 0.8361
## 95% CI : (0.8144, 0.8562)
## No Information Rate : 0.7322
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.534
##
## Mcnemar's Test P-Value : 4.591e-14
##
## Sensitivity : 0.5313
## Specificity : 0.9476
## Pos Pred Value : 0.7876
## Neg Pred Value : 0.8468
## Precision : 0.7876
## Recall : 0.5313
## F1 : 0.6346
## Prevalence : 0.2678
## Detection Rate : 0.1423
## Detection Prevalence : 0.1807
## Balanced Accuracy : 0.7395
##
## 'Positive' Class : Churned
##
vif(md1)
## GVIF Df GVIF^(1/(2*Df))
## Gender 1.003156 1 1.001577
## `Age Group` 1.069192 2 1.016866
## Married 2.025361 1 1.423152
## `Number of Dependents` 1.088773 1 1.043443
## `Number of Referrals` 1.738341 1 1.318462
## `Tenure in Months` 21.707871 1 4.659171
## `Avg Monthly Long Distance Charges` 1.343572 1 1.159125
## `Multiple Lines` 1.403045 1 1.184502
## Contract 1.440901 2 1.095617
## `Paperless Billing` 1.129956 1 1.062994
## `Payment Method` 1.147093 2 1.034903
## `Monthly Charge` 2.307393 1 1.519010
## `Total Revenue` 25.472390 1 5.047018
- Offer A seems to be the most effective when it has a high amount of revenue compared to other types even though the monthly payment is the same. The only weakness is that the number of users of offer A is relatively low
=> R&D department: need to vary offers with different prices and terms
=> Marketing department: should have some promotions for this offer
-45% of customers churn and switch to competitors, this could be from high price, service quality or negative experiences. Especially, contract month-to-month have large churned customers.
=> Need care and adjust immediately this contract type
-Factors that increase churn rate from large to small are: (1) Married, (2) Age group from 60 - 89, (3) Mailed Check, (4) Paperless billing, (5) Multiple Lines and (6) Monthly Charge
=> Need some specific policies