Himanshi Tanwar

Forecasting Air Quality Using Machine Learning Regression Models

•       Built an end-to-end ML pipeline to predict Air Quality Index (AQI)

•       Performed preprocessing, feature engineering, and missing value handling

•       Implemented and compared Random Forest and Linear Regression models

•       Evaluated using RMSE, MAE, and R²; analysed key pollutant features

ChurnAI — Full Stack Customer Churn Prediction Dashboard

Built a full-stack customer churn prediction dashboard with an end-to-end machine learning pipeline.

Performed data preprocessing, feature engineering, feature selection, and class balancing (SMOTE).

Trained and compared Logistic Regression, Decision Tree, Random Forest, MLP, and XGBoost models.

Evaluated models using Accuracy, Precision, Recall, F1-score, and AUC-ROC; integrated forecasting and retention recommendations.

EnviroSense Pro — AI-Based Smart Environmental Monitoring & Disaster Prediction System |

Built an end-to-end AI-powered environmental monitoring system with a Flask-based interactive dashboard.

Performed data preprocessing, feature engineering, and trained multiple ML models for disaster risk prediction.

Developed real-time weather monitoring, disaster alerts, forecasting, and location-based risk visualization.

Evaluated and compared Random Forest, XGBoost, Gradient Boosting, Decision Tree, and Logistic Regression models.

Tech: