grwyn/Customer-Churn-at-Botswana-Bank

# Customer Churn at Botswana Bank Dataset source : kaggle.com Deployment link : huggingface.co Name : Gerwyn Zulqarnain There are six models that will be used for training in this project, along with a brief explanation of each model: Logistic Regression: A linear model used for binary classification that predicts the probability of a class (usually 0 or 1) by using a logistic function. Decision Trees: A tree-like model where data is split based on features to make predictions. Each node represents a decision based on a feature, and the leaves represent the output class. Random Forest: An ensemble learning method that combines multiple decision trees to improve accuracy and reduce overfitting by averaging their predictions. Support Vector Classifier (SVC): A classification algorithm that finds the best boundary (hyperplane) between classes by maximizing the margin between the closest data points of different classes. K-Nearest Neighbors (KNN): A simple algorithm that classifies data points based on the majority class of their nearest neighbors in the feature space. XGBoost: A powerful and efficient gradient-boosting algorithm that builds an ensemble of weak decision trees in a sequential manner, improving model performance by minimizing prediction errors. The goal of this project is to build a robust machine learning pipeline to analyze customer churn at a Botswana bank. By exploring multiple classification models, we aim to identify the best-performing model based on the F1 score, which balances both precision and recall, minimizing false negatives and false positives. This will help the bank accurately predict customers likely to churn and implement targeted business strategies. The ultimate objective is to improve customer retention by leveraging insights from the machine learning model to understand the key factors driving churn, enabling the bank to optimize its cu …