app.py

import streamlit as st
import eda
import models


page = st.sidebar.selectbox(label='Select Page:', options=['Home Page', 'Exploratory Data Analysis', 'Prediction Models'])

if page == 'Home Page':
    st.header('Customer Churn Prediction !') 
    st.write('')
    st.write('Project of Milestone 2')
    st.write('Nama      : Anjas Fajar Maulana')
    st.write('Batch     : HCK014')
    st.write('Objective    : The goal of this project is to build a machine learning model that can predict customer churn at DXTR Provider. The predictive machine learning model is using `K-Nearest Neighbor (KNN) Classifier`, `Support Vector Classification (SVC)`, `Decision Tree Classifier`, `Random Forest Classifier`and `Boosting` Algorithms `XGB Classifier`, then identify the best model for predicting customers who have the potential to leave provider services. This model helps company identify customers at high risk of churning, enabling them to take further action to retain customers and prevent potential business losses.')
    st.write('')
    st.caption('Please select another menu in the Select Box on the left side of your screen to get started !')
    st.write('')
    st.write('')
    with st.expander("Background"):
        st.caption("Lately, customer churn from the company is quite high so to minimize it we must be able to predict what factors make customer churn, in order to further develop the company's performance.")

    with st.expander("Problem Statement"):
            st.caption("Predict customer churn to prevent or reduce churn, by retaining existing customers and preventing them from leaving the company's products or services. by creating a predictive machine learning model using KNN, SVM, Decision Tree, Random Forest, and Boosting algorithms, then identify the best model for predicting customers who have the potential to leave bank services. This model helps banks identify customers at high risk of churning, enabling them to take further action to retain customers and prevent potential business losses.")

    with st.expander("Conclusion"):
        st.caption('Using Model Machine Learning we can predict whether the customer is will Churn or Not')
elif page == 'Exploratory Data Analysis':
    eda.run()
else:
    models.run()