Project : Modeling Telco Customer Churn

A. Data Description

The dataset includes information about:

Customers who left within the last month – the column is called Churn
Services that each customer has signed up for – phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and movies
Customer account information – how long they’ve been a customer, contract, payment method, paperless billing, monthly charges, and total charges
Demographic info about customers – gender, age range, and if they have partners and dependents

==================================================================================================================

B. Data Analysis:

show directory location

# mendapatkan lokasi directory pengerjaan
getwd()

## [1] "D:/BINUS UNIVERSITY/SEMESTER 5/Bayessian"

Import dataset

# loading dataset
file_path <- "WA_Fn-UseC_-Telco-Customer-Churn.csv"
data <- read.csv(file_path, stringsAsFactors = FALSE)

# Menampilkan beberapa baris awal 
kable(head(data))

customerID	gender	Partner	Dependents	tenure	PhoneService	MultipleLines	InternetService	OnlineSecurity	OnlineBackup	DeviceProtection	TechSupport	StreamingTV	StreamingMovies	Contract	PaperlessBilling	PaymentMethod	MonthlyCharges	TotalCharges	Churn
7590-VHVEG	Female	Yes	No	1	No	No phone service	DSL	No	Yes	No	No	No	No	Month-to-month	Yes	Electronic check	29.85	29.85	No
5575-GNVDE	Male	No	No	34	Yes	No	DSL	Yes	No	Yes	No	No	No	One year	No	Mailed check	56.95	1889.50	No
3668-QPYBK	Male	No	No	2	Yes	No	DSL	Yes	Yes	No	No	No	No	Month-to-month	Yes	Mailed check	53.85	108.15	Yes
7795-CFOCW	Male	No	No	45	No	No phone service	DSL	Yes	No	Yes	Yes	No	No	One year	No	Bank transfer (automatic)	42.30	1840.75	No
9237-HQITU	Female	No	No	2	Yes	No	Fiber optic	No	No	No	No	No	No	Month-to-month	Yes	Electronic check	70.70	151.65	Yes
9305-CDSKC	Female	No	No	8	Yes	Yes	Fiber optic	No	No	Yes	No	Yes	Yes	Month-to-month	Yes	Electronic check	99.65	820.50	Yes

Checking Dataset

str(data)

## 'data.frame':    7043 obs. of  21 variables:
##  $ customerID      : chr  "7590-VHVEG" "5575-GNVDE" "3668-QPYBK" "7795-CFOCW" ...
##  $ gender          : chr  "Female" "Male" "Male" "Male" ...
##  $ SeniorCitizen   : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ Partner         : chr  "Yes" "No" "No" "No" ...
##  $ Dependents      : chr  "No" "No" "No" "No" ...
##  $ tenure          : int  1 34 2 45 2 8 22 10 28 62 ...
##  $ PhoneService    : chr  "No" "Yes" "Yes" "No" ...
##  $ MultipleLines   : chr  "No phone service" "No" "No" "No phone service" ...
##  $ InternetService : chr  "DSL" "DSL" "DSL" "DSL" ...
##  $ OnlineSecurity  : chr  "No" "Yes" "Yes" "Yes" ...
##  $ OnlineBackup    : chr  "Yes" "No" "Yes" "No" ...
##  $ DeviceProtection: chr  "No" "Yes" "No" "Yes" ...
##  $ TechSupport     : chr  "No" "No" "No" "Yes" ...
##  $ StreamingTV     : chr  "No" "No" "No" "No" ...
##  $ StreamingMovies : chr  "No" "No" "No" "No" ...
##  $ Contract        : chr  "Month-to-month" "One year" "Month-to-month" "One year" ...
##  $ PaperlessBilling: chr  "Yes" "No" "Yes" "No" ...
##  $ PaymentMethod   : chr  "Electronic check" "Mailed check" "Mailed check" "Bank transfer (automatic)" ...
##  $ MonthlyCharges  : num  29.9 57 53.9 42.3 70.7 ...
##  $ TotalCharges    : num  29.9 1889.5 108.2 1840.8 151.7 ...
##  $ Churn           : chr  "No" "No" "Yes" "No" ...

Checking Null Value

# Mengecek jumlah nilai yang hilang
kable(colSums(is.na(data)))

	x
customerID	0
gender	0
SeniorCitizen	0
Partner	0
Dependents	0
tenure	0
PhoneService	0
MultipleLines	0
InternetService	0
OnlineSecurity	0
OnlineBackup	0
DeviceProtection	0
TechSupport	0
StreamingTV	0
StreamingMovies	0
Contract	0
PaperlessBilling	0
PaymentMethod	0
MonthlyCharges	0
TotalCharges	11
Churn	0

There is null value in feature “TotalCharge”

==================================================================================================================

C. Data Processing:

Cleaning data

# Menghapus baris dengan NA pada 'TotalCharges'
cleaned_data <- na.omit(data)

# Memeriksa ulang dataset setelah pembersihan
str(cleaned_data)

## 'data.frame':    7032 obs. of  21 variables:
##  $ customerID      : chr  "7590-VHVEG" "5575-GNVDE" "3668-QPYBK" "7795-CFOCW" ...
##  $ gender          : chr  "Female" "Male" "Male" "Male" ...
##  $ SeniorCitizen   : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ Partner         : chr  "Yes" "No" "No" "No" ...
##  $ Dependents      : chr  "No" "No" "No" "No" ...
##  $ tenure          : int  1 34 2 45 2 8 22 10 28 62 ...
##  $ PhoneService    : chr  "No" "Yes" "Yes" "No" ...
##  $ MultipleLines   : chr  "No phone service" "No" "No" "No phone service" ...
##  $ InternetService : chr  "DSL" "DSL" "DSL" "DSL" ...
##  $ OnlineSecurity  : chr  "No" "Yes" "Yes" "Yes" ...
##  $ OnlineBackup    : chr  "Yes" "No" "Yes" "No" ...
##  $ DeviceProtection: chr  "No" "Yes" "No" "Yes" ...
##  $ TechSupport     : chr  "No" "No" "No" "Yes" ...
##  $ StreamingTV     : chr  "No" "No" "No" "No" ...
##  $ StreamingMovies : chr  "No" "No" "No" "No" ...
##  $ Contract        : chr  "Month-to-month" "One year" "Month-to-month" "One year" ...
##  $ PaperlessBilling: chr  "Yes" "No" "Yes" "No" ...
##  $ PaymentMethod   : chr  "Electronic check" "Mailed check" "Mailed check" "Bank transfer (automatic)" ...
##  $ MonthlyCharges  : num  29.9 57 53.9 42.3 70.7 ...
##  $ TotalCharges    : num  29.9 1889.5 108.2 1840.8 151.7 ...
##  $ Churn           : chr  "No" "No" "Yes" "No" ...
##  - attr(*, "na.action")= 'omit' Named int [1:11] 489 754 937 1083 1341 3332 3827 4381 5219 6671 ...
##   ..- attr(*, "names")= chr [1:11] "489" "754" "937" "1083" ...

Save cleaned dataset

# Menyimpan dataset yang telah dibersihkan
write.csv(cleaned_data, "cleaned_telco_churn.csv", row.names = FALSE)

# Menampilkan lokasi file
cat("Dataset telah disimpan sebagai 'cleaned_telco_churn.csv'")

## Dataset telah disimpan sebagai 'cleaned_telco_churn.csv'

==================================================================================================================

D. Modeling:

show package

#install.packages("brms")
#install.packages("loo") # Untuk model comparison

show code import cleaned_data

# loading dataset
file_path <- "cleaned_telco_churn.csv"
data <- read.csv(file_path, stringsAsFactors = FALSE)

A. Model 1 : Prior Uninformative

library(brms)

# Model pertama: Regresi logistik dengan prior default
model1 <- brm(
  formula = Churn ~ tenure + MonthlyCharges + TotalCharges + SeniorCitizen,
  family = bernoulli(link = "logit"),
  data = data,
  prior = set_prior("", class = "b"), # Uninformative prior
  chains = 4, iter = 200, warmup = 10, seed = 123
)

## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 1).
## Chain 1: 
## Chain 1: Gradient evaluation took 0.000177 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 1.77 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1: 
## Chain 1: 
## Chain 1: WARNING: No variance estimation is
## Chain 1:          performed for num_warmup < 20
## Chain 1: 
## Chain 1: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 1: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 1: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 1: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 1: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 1: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 1: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 1: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 1: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 1: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 1: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 1: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.006 seconds (Warm-up)
## Chain 1:                0.114 seconds (Sampling)
## Chain 1:                0.12 seconds (Total)
## Chain 1: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 2).
## Chain 2: 
## Chain 2: Gradient evaluation took 0.000194 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 1.94 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2: 
## Chain 2: 
## Chain 2: WARNING: No variance estimation is
## Chain 2:          performed for num_warmup < 20
## Chain 2: 
## Chain 2: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 2: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 2: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 2: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 2: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 2: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 2: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 2: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 2: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 2: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 2: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 2: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.004 seconds (Warm-up)
## Chain 2:                0.077 seconds (Sampling)
## Chain 2:                0.081 seconds (Total)
## Chain 2: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 3).
## Chain 3: 
## Chain 3: Gradient evaluation took 0.000207 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 2.07 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3: 
## Chain 3: 
## Chain 3: WARNING: No variance estimation is
## Chain 3:          performed for num_warmup < 20
## Chain 3: 
## Chain 3: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 3: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 3: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 3: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 3: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 3: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 3: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 3: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 3: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 3: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 3: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 3: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.005 seconds (Warm-up)
## Chain 3:                0.071 seconds (Sampling)
## Chain 3:                0.076 seconds (Total)
## Chain 3: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 4).
## Chain 4: 
## Chain 4: Gradient evaluation took 0.000203 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 2.03 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4: 
## Chain 4: 
## Chain 4: WARNING: No variance estimation is
## Chain 4:          performed for num_warmup < 20
## Chain 4: 
## Chain 4: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 4: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 4: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 4: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 4: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 4: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 4: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 4: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 4: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 4: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 4: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 4: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.005 seconds (Warm-up)
## Chain 4:                0.071 seconds (Sampling)
## Chain 4:                0.076 seconds (Total)
## Chain 4:

Explanation :

Description: This model uses a logistic regression approach to predict customer churn (Churn). It applies uninformative priors, meaning it does not include strong assumptions about the coefficients beforehand. The priors for all predictors are weak and set by default.
Parameters:
- tenure: The number of months a customer has been with the company.
- MonthlyCharges: The monthly charges for the customer.
- TotalCharges: The total charges incurred by the customer.
- SeniorCitizen: Indicates whether the customer is a senior citizen (1 = Yes, 0 = No).
Settings:
- Chains: 4 (to ensure robust sampling).
- Iterations: 2000 (with 1000 warm-up iterations for convergence).
- Seed: 123 (to ensure reproducibility).

This model is intended to serve as a baseline without incorporating domain knowledge or prior assumptions.

A. Model 2 : Prior Informative

# Prior informative
prior2 <- c(
  set_prior("normal(0, 5)", class = "b", coef = "MonthlyCharges"),
  set_prior("normal(0, 10)", class = "b") # Prior lemah untuk lainnya
)

# Model kedua: Regresi logistik dengan prior informative
model2 <- brm(
  formula = Churn ~ tenure + MonthlyCharges + TotalCharges + SeniorCitizen,
  family = bernoulli(link = "logit"),
  data = data,
  prior = prior2,
  chains = 4, iter = 200, warmup = 10, seed = 123
)

## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 1).
## Chain 1: 
## Chain 1: Gradient evaluation took 0.000186 seconds
## Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 1.86 seconds.
## Chain 1: Adjust your expectations accordingly!
## Chain 1: 
## Chain 1: 
## Chain 1: WARNING: No variance estimation is
## Chain 1:          performed for num_warmup < 20
## Chain 1: 
## Chain 1: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 1: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 1: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 1: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 1: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 1: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 1: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 1: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 1: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 1: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 1: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 1: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 1: 
## Chain 1:  Elapsed Time: 0.006 seconds (Warm-up)
## Chain 1:                0.114 seconds (Sampling)
## Chain 1:                0.12 seconds (Total)
## Chain 1: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 2).
## Chain 2: 
## Chain 2: Gradient evaluation took 0.000202 seconds
## Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 2.02 seconds.
## Chain 2: Adjust your expectations accordingly!
## Chain 2: 
## Chain 2: 
## Chain 2: WARNING: No variance estimation is
## Chain 2:          performed for num_warmup < 20
## Chain 2: 
## Chain 2: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 2: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 2: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 2: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 2: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 2: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 2: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 2: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 2: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 2: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 2: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 2: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 2: 
## Chain 2:  Elapsed Time: 0.004 seconds (Warm-up)
## Chain 2:                0.078 seconds (Sampling)
## Chain 2:                0.082 seconds (Total)
## Chain 2: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 3).
## Chain 3: 
## Chain 3: Gradient evaluation took 0.000202 seconds
## Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 2.02 seconds.
## Chain 3: Adjust your expectations accordingly!
## Chain 3: 
## Chain 3: 
## Chain 3: WARNING: No variance estimation is
## Chain 3:          performed for num_warmup < 20
## Chain 3: 
## Chain 3: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 3: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 3: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 3: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 3: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 3: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 3: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 3: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 3: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 3: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 3: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 3: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 3: 
## Chain 3:  Elapsed Time: 0.005 seconds (Warm-up)
## Chain 3:                0.072 seconds (Sampling)
## Chain 3:                0.077 seconds (Total)
## Chain 3: 
## 
## SAMPLING FOR MODEL 'anon_model' NOW (CHAIN 4).
## Chain 4: 
## Chain 4: Gradient evaluation took 0.000205 seconds
## Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 2.05 seconds.
## Chain 4: Adjust your expectations accordingly!
## Chain 4: 
## Chain 4: 
## Chain 4: WARNING: No variance estimation is
## Chain 4:          performed for num_warmup < 20
## Chain 4: 
## Chain 4: Iteration:   1 / 200 [  0%]  (Warmup)
## Chain 4: Iteration:  11 / 200 [  5%]  (Sampling)
## Chain 4: Iteration:  30 / 200 [ 15%]  (Sampling)
## Chain 4: Iteration:  50 / 200 [ 25%]  (Sampling)
## Chain 4: Iteration:  70 / 200 [ 35%]  (Sampling)
## Chain 4: Iteration:  90 / 200 [ 45%]  (Sampling)
## Chain 4: Iteration: 110 / 200 [ 55%]  (Sampling)
## Chain 4: Iteration: 130 / 200 [ 65%]  (Sampling)
## Chain 4: Iteration: 150 / 200 [ 75%]  (Sampling)
## Chain 4: Iteration: 170 / 200 [ 85%]  (Sampling)
## Chain 4: Iteration: 190 / 200 [ 95%]  (Sampling)
## Chain 4: Iteration: 200 / 200 [100%]  (Sampling)
## Chain 4: 
## Chain 4:  Elapsed Time: 0.005 seconds (Warm-up)
## Chain 4:                0.071 seconds (Sampling)
## Chain 4:                0.076 seconds (Total)
## Chain 4:

Explanation :

Description: This model is similar to Model 1 in structure but incorporates informative priors. These priors are based on domain knowledge or previous studies. For example, it assumes that MonthlyCharges significantly influences churn, and this influence is captured with a Normal(0, 5) prior for its coefficient.
Parameters:
- The predictors (tenure, MonthlyCharges, TotalCharges, SeniorCitizen) are the same as in Model 1.
- Informative prior for MonthlyCharges: Normal(0, 5).
- Weak priors for other predictors: Normal(0, 10).
Settings:
- Chains: 4.
- Iterations: 2000 (1000 warm-up).
- Seed: 123.

This model leverages prior information to refine predictions, enabling better comparison with the uninformative model.

==================================================================================================================

F. Comparasion model:

summary(model1)  # R-hat dan konvergensi untuk model pertama

##  Family: bernoulli 
##   Links: mu = logit 
## Formula: Churn ~ tenure + MonthlyCharges + TotalCharges + SeniorCitizen 
##    Data: data (Number of observations: 7032) 
##   Draws: 4 chains, each with iter = 200; warmup = 10; thin = 1;
##          total post-warmup draws = 760
## 
## Regression Coefficients:
##                Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept          9.86     39.95   -38.22    56.21  Inf        4       NA
## tenure             0.56      0.58    -0.42     1.05  Inf        4       NA
## MonthlyCharges    -0.03      0.95    -1.14     1.07  Inf        4       NA
## TotalCharges      -0.01      0.02    -0.04     0.01  Inf        4       NA
## SeniorCitizen      0.54      1.07    -1.03     1.81  Inf        4       NA
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

summary(model2)  # R-hat dan konvergensi untuk model kedua

##  Family: bernoulli 
##   Links: mu = logit 
## Formula: Churn ~ tenure + MonthlyCharges + TotalCharges + SeniorCitizen 
##    Data: data (Number of observations: 7032) 
##   Draws: 4 chains, each with iter = 200; warmup = 10; thin = 1;
##          total post-warmup draws = 760
## 
## Regression Coefficients:
##                Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept          9.86     39.95   -38.22    56.21  Inf        4       NA
## tenure             0.56      0.58    -0.42     1.05  Inf        4       NA
## MonthlyCharges    -0.03      0.95    -1.14     1.07  Inf        4       NA
## TotalCharges      -0.01      0.02    -0.04     0.01  Inf        4       NA
## SeniorCitizen      0.54      1.07    -1.03     1.81  Inf        4       NA
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

# Plot trace untuk masing-masing model
plot(model1)

plot(model2)

compare 2 model

==================================================================================================================

G. Conclusion:

In conclusion, the analysis of social assistance distribution in Bandung City reveals that these programs are not only well-targeted but also effective in reaching the most impoverished areas. This alignment with the Sustainable Development Goal of No Poverty underscores the city government’s commitment to addressing socio-economic disparities. Moving forward, continuous monitoring and evaluation will be crucial to ensure these efforts remain responsive to evolving community needs and contribute effectively to long-term poverty alleviation strategies.

==================================================================================================================

H. Refrence:

==================================================================================================================

Project : Modeling Telco Customer Churn

Rendra Dwi Prasetyo - 2602199960

2024-06-14

A. Data Description

B. Data Analysis:

C. Data Processing:

D. Modeling:

Explanation :

Explanation :

F. Comparasion model:

G. Conclusion:

H. Refrence: