📘 MACHINE LEARNING PROJECTS PORTFOLIO
A collection of machine learning projects ranging from beginner to advanced level, covering classification, regression, NLP, recommendation systems, and explainable AI.
🟢 Beginner Projects
- Telecom Customer Churn Prediction
A classification project that predicts whether a telecom customer will leave the service based on demographic details, account information, and subscribed services. It uses Decision Tree and Random Forest models to identify at-risk customers and support retention strategies.
🔗 Dataset: https://www.kaggle.com/datasets/blastchar/telco-customer-churn
- SMS Spam Detection System
A natural language processing (NLP) project that classifies SMS messages as spam or ham using TF-IDF vectorization and Naive Bayes algorithms. It helps in filtering unwanted messages and improving communication security.
🔗 Dataset: https://www.kaggle.com/datasets/uciml/sms-spam-collection-dataset
- Wine Quality Prediction System
A machine learning classification project that predicts the quality of red wine based on physicochemical properties such as acidity, alcohol content, pH, and sulphates. Random Forest is used for high-accuracy prediction.
🔗 Dataset: https://www.kaggle.com/datasets/uciml/red-wine-quality-cortez-et-al-2009
- Medical Insurance Cost Prediction
A regression-based machine learning project that predicts individual medical insurance charges using features like age, BMI, smoking status, number of children, and region. Linear Regression is used to estimate costs.
🔗 Dataset: https://www.kaggle.com/datasets/mirichoi0218/insurance
🔵 Advanced Projects
- Movie Recommendation System
A collaborative filtering-based recommendation system that suggests movies based on user preferences and similarity between movies. It uses K-Nearest Neighbors (KNN) and cosine similarity to generate personalized recommendations.
🔗 Dataset: https://www.kaggle.com/datasets/parasharmanas/movie-recommendation-system
- Explainable SMS Spam Classifier (LIME & SHAP)
An advanced NLP-based spam detection system that not only classifies SMS messages as spam or ham but also explains predictions using Explainable AI techniques like LIME and SHAP, making the model transparent and interpretable.
🔗 Dataset: https://www.kaggle.com/datasets/uciml/sms-spam-collection-dataset