Tag: Machine Learning
All the articles with the tag "Machine Learning".
-
Hybrid Book Recommender System
A book recommendation system combining content-based filtering (TF-IDF), collaborative filtering (user similarity), and network-based recommendation (PageRank) into a hybrid architecture — with separate cold-start and warm-user routing.
-
Type II Diabetes Risk Prediction – Published Research
A multiclass ML system predicting Type II diabetes risk from NHANES lab and lifestyle data, published in IEEE. Built a full pipeline with LightGBM, Optuna, MLflow, and feature ablation studies.
-
DDoS Attack Classifier – ML-Based Network Traffic Analysis
A machine learning project for classifying DDoS attack traffic, comparing Logistic Regression, Autoencoders, and DBSCAN on the Kaggle DDoS dataset — with production-ready sklearn-compatible preprocessing pipelines.
-
Room Occupancy Detection – Time-Series-Aware ML from Sensor Data
A machine learning project predicting room occupancy from environmental sensors — with careful time-series cross-validation, SMOTE for class imbalance, model comparison across Random Forest, XGBoost, and LightGBM, and SHAP-based interpretability.