diff --git a/models/Gradient_Boosting.joblib b/models/Gradient_Boosting.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..3455361eecab029a6cec4202a5eb73d62d29d33c
Binary files /dev/null and b/models/Gradient_Boosting.joblib differ
diff --git a/models/K-Nearest_Neighbors.joblib b/models/K-Nearest_Neighbors.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..b750959d9b601e983d695c0faa0db43bddd52bfe
Binary files /dev/null and b/models/K-Nearest_Neighbors.joblib differ
diff --git a/models/Logistic_Regression.joblib b/models/Logistic_Regression.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..a6577106112ba5333fe14e7b1c9b70cc1e3bcbc9
Binary files /dev/null and b/models/Logistic_Regression.joblib differ
diff --git a/models/Random_Forest.joblib b/models/Random_Forest.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..4ae9b15db751bb261d077bcbcd0fa63bd6c2f9a8
Binary files /dev/null and b/models/Random_Forest.joblib differ
diff --git a/models/Support_Vector_Machine.joblib b/models/Support_Vector_Machine.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..118dc2fa6ff6ae1ced1377b1cb5b0a524eb24b7c
Binary files /dev/null and b/models/Support_Vector_Machine.joblib differ
diff --git a/models/XGBoost.joblib b/models/XGBoost.joblib
new file mode 100644
index 0000000000000000000000000000000000000000..3a785476e65488ba5b5ec2c70a1baf4a8ae8bd07
Binary files /dev/null and b/models/XGBoost.joblib differ
diff --git a/notebooks/customer_churn_machine_learning_models.ipynb b/notebooks/customer_churn_machine_learning_models.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..f4da41f5504d82521093635f0c661e85aeff8352
--- /dev/null
+++ b/notebooks/customer_churn_machine_learning_models.ipynb
@@ -0,0 +1,293 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Customer Churn Prediction: Machine Learning Models \n",
+ "\n",
+ "This notebook will load the training, validation, and test datasets, train multiple machine learning models, evaluate their performance, and save the models for future use. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Import Libraries \n",
+ "import pandas as pd \n",
+ "import numpy as np \n",
+ "from sklearn.model_selection import train_test_split \n",
+ "from sklearn.ensemble import RandomForestClassifier \n",
+ "from sklearn.linear_model import LogisticRegression \n",
+ "from sklearn.metrics import accuracy_score, classification_report \n",
+ "from sklearn.preprocessing import StandardScaler \n",
+ "import joblib \n",
+ "\n",
+ "from sklearn.svm import SVC \n",
+ "from sklearn.ensemble import GradientBoostingClassifier \n",
+ "from sklearn.neighbors import KNeighborsClassifier \n",
+ "from xgboost import XGBClassifier\n",
+ "\n",
+ "# Set display options for better readability \n",
+ "pd.set_option('display.max_columns', None) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1. Load the Data \n",
+ "\n",
+ "Load the training, validation, and test datasets that we saved in the preprocessing step. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Training set size: 5977\n",
+ "Validation set size: 527\n",
+ "Test set size: 528\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load the datasets \n",
+ "X_train = pd.read_csv('../data/X_train.csv') \n",
+ "y_train = pd.read_csv('../data/y_train.csv') \n",
+ "X_val = pd.read_csv('../data/X_val.csv') \n",
+ "y_val = pd.read_csv('../data/y_val.csv') \n",
+ "X_test = pd.read_csv('../data/X_test.csv') \n",
+ "y_test = pd.read_csv('../data/y_test.csv') \n",
+ "\n",
+ "# Display the shapes of the datasets \n",
+ "print(f\"Training set size: {X_train.shape[0]}\") \n",
+ "print(f\"Validation set size: {X_val.shape[0]}\") \n",
+ "print(f\"Test set size: {X_test.shape[0]}\") "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 2. Scale the Data \n",
+ "\n",
+ "Scale the features using StandardScaler. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Initialize the scaler \n",
+ "scaler = StandardScaler() \n",
+ "\n",
+ "# Fit the scaler on the training data and transform the training, validation, and test sets \n",
+ "X_train_scaled = scaler.fit_transform(X_train) \n",
+ "X_val_scaled = scaler.transform(X_val) \n",
+ "X_test_scaled = scaler.transform(X_test) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 3. Model Training \n",
+ "\n",
+ "Train multiple machine learning models "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Logistic Regression Validation Accuracy: 0.8027\n",
+ "Random Forest Validation Accuracy: 0.7742\n",
+ "Support Vector Machine Validation Accuracy: 0.7989\n",
+ "Gradient Boosting Validation Accuracy: 0.7951\n",
+ "K-Nearest Neighbors Validation Accuracy: 0.7666\n",
+ "XGBoost Validation Accuracy: 0.7837\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Initialize models \n",
+ "models = { \n",
+ " 'Logistic Regression': LogisticRegression(max_iter=2000), \n",
+ " 'Random Forest': RandomForestClassifier(n_estimators=100, random_state=127), \n",
+ " 'Support Vector Machine': SVC(probability=True), \n",
+ " 'Gradient Boosting': GradientBoostingClassifier(n_estimators=100, random_state=127), \n",
+ " 'K-Nearest Neighbors': KNeighborsClassifier(n_neighbors=5), \n",
+ " 'XGBoost': XGBClassifier(eval_metric='logloss') \n",
+ "} \n",
+ "\n",
+ "# Train models and evaluate on the validation set \n",
+ "for model_name, model in models.items(): \n",
+ " model.fit(X_train_scaled, y_train.values.ravel()) \n",
+ " y_val_pred = model.predict(X_val_scaled) \n",
+ " accuracy = accuracy_score(y_val, y_val_pred) \n",
+ " print(f\"{model_name} Validation Accuracy: {accuracy:.4f}\") "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 4. Save the Models \n",
+ "\n",
+ "Save the trained models for future use. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Logistic Regression saved successfully.\n",
+ "Random Forest saved successfully.\n",
+ "Support Vector Machine saved successfully.\n",
+ "Gradient Boosting saved successfully.\n",
+ "K-Nearest Neighbors saved successfully.\n",
+ "XGBoost saved successfully.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Save each model \n",
+ "for model_name, model in models.items(): \n",
+ " joblib.dump(model, f'../models/{model_name.replace(\" \", \"_\")}.joblib') \n",
+ " print(f\"{model_name} saved successfully.\") "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 5. Load and Evaluate the Models \n",
+ "\n",
+ "Load the saved models and evaluate them on the test set. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Logistic Regression Test Accuracy: 0.8030\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.84 0.90 0.87 388\n",
+ " 1 0.66 0.54 0.59 140\n",
+ "\n",
+ " accuracy 0.80 528\n",
+ " macro avg 0.75 0.72 0.73 528\n",
+ "weighted avg 0.79 0.80 0.80 528\n",
+ "\n",
+ "Random Forest Test Accuracy: 0.7841\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.82 0.91 0.86 388\n",
+ " 1 0.63 0.44 0.52 140\n",
+ "\n",
+ " accuracy 0.78 528\n",
+ " macro avg 0.73 0.68 0.69 528\n",
+ "weighted avg 0.77 0.78 0.77 528\n",
+ "\n",
+ "Support Vector Machine Test Accuracy: 0.8087\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.84 0.92 0.88 388\n",
+ " 1 0.69 0.51 0.58 140\n",
+ "\n",
+ " accuracy 0.81 528\n",
+ " macro avg 0.76 0.71 0.73 528\n",
+ "weighted avg 0.80 0.81 0.80 528\n",
+ "\n",
+ "Gradient Boosting Test Accuracy: 0.8030\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.84 0.91 0.87 388\n",
+ " 1 0.67 0.51 0.58 140\n",
+ "\n",
+ " accuracy 0.80 528\n",
+ " macro avg 0.75 0.71 0.72 528\n",
+ "weighted avg 0.79 0.80 0.79 528\n",
+ "\n",
+ "K-Nearest Neighbors Test Accuracy: 0.7746\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.83 0.87 0.85 388\n",
+ " 1 0.58 0.52 0.55 140\n",
+ "\n",
+ " accuracy 0.77 528\n",
+ " macro avg 0.71 0.69 0.70 528\n",
+ "weighted avg 0.77 0.77 0.77 528\n",
+ "\n",
+ "XGBoost Test Accuracy: 0.7765\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.82 0.88 0.85 388\n",
+ " 1 0.60 0.48 0.53 140\n",
+ "\n",
+ " accuracy 0.78 528\n",
+ " macro avg 0.71 0.68 0.69 528\n",
+ "weighted avg 0.76 0.78 0.77 528\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Load and evaluate each model on the test set \n",
+ "for model_name in models.keys(): \n",
+ " loaded_model = joblib.load(f'../models/{model_name.replace(\" \", \"_\")}.joblib') \n",
+ " y_test_pred = loaded_model.predict(X_test_scaled) \n",
+ " accuracy = accuracy_score(y_test, y_test_pred) \n",
+ " print(f\"{model_name} Test Accuracy: {accuracy:.4f}\") \n",
+ " print(classification_report(y_test, y_test_pred)) "
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.11.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}