Bank Customer Churn Prediction

• This document will take you through the summary of this project with a result at the rend

• Please check the requirements.txt file for the libraries used in the project.

• This notebook contains the Exploratory Data Analysis of the dataset. the definition of the columns are as follows:'
• RowNumber: Row Numbers from 1 to 10000
• CustomerId: Unique Ids for bank customer identification
• Surname: Customer's last name
• CreditScore: Credit score of the customer
• Age: Customer's age in years
• Tenure: Number of years for which the customer has been with the bank
• Balance: Bank balance of the customer
• NumOfProducts: Number of bank products the customer is utilising
• HasCrCard: Binary Flag for whether the customer holds a credit card with the bank or not
• IsActiveMember: Binary Flag for whether the customer is an active member with the bank or not
• EstimatedSalary: Estimated salary of the customer in Dollars
• churn : Binary flag 1 or 0

• Data Cleaning
• Data Visualization
• Data Preprocessing
• Feature Selection
• Model Building
• Model Evaluation
• Model Deployment

• This file contains the code for the deployment of the model using streamlit. -[x] below is the import of the libraries used in the file.

import streamlit as st
import joblib
import pandas as pd
import numpy as np
import eli5
from eli5 import explain_weights, explain_prediction

• Below we load xgboost model using joblib.

#load the xgboost model
model = joblib.load('xgb_model.pkl')

• Call feature_names function to get the feature names.

#call feature_names function to get the feature names
st.title('Bank Customer Churn Prediction')
age = st.number_input('Age', min_value=18, max_value=100, value=18)
credit_score = st.number_input('Credit Score', min_value=300, max_value=850, value=300)
balance = st.number_input('Balance', min_value=0, max_value=250000, value=0)
num_of_products = st.number_input('Number of Products', min_value=1, max_value=4, value=1)
tenure = st.number_input('Tenure', min_value=0, max_value=10, value=0)
has_cr_card = st.selectbox('Has Credit Card', ['Yes','No'])
is_active_member = st.selectbox('Is Active Member', ['Yes','No'])
gender = st.selectbox('Gender',['Male','Female'])
estimated_salary = st.number_input('Estimated Salary', min_value=0, max_value=250000, value=0)
geography = st.selectbox('Geography', ['France', 'Germany', 'Spain'])

• Below we create a dictionary of the input values.

# create a dictionary of inputs
features = pd.Dataframe({'age':age, 'credit_score': credit_score,....})

the rest is history, do feel free to catch on the rest of the code in the file.

• The model was deployed using streamlit.
• The duration of the project was 3 hours.
• Enjoy the app. pleae do leave a feedback.
• Find here the link to the app https://bank-churn-customer.streamlit.app/
• Thank you.