Applied ML for Business & Industrial Forecasting

Project Overview

Designed and implemented multiple supervised machine learning pipelines to solve real-world classification and regression problems
Built feedforward neural network (FFN) models to classify customer subscription likelihood using behavioral and demographic features
Developed regression models to predict vehicle emission levels (PPM), enabling data-driven environmental compliance
Implemented machine learning models to forecast interest rates based on historical financial and macroeconomic indicators
Modeled counterfeit medicine sales patterns to support demand forecasting and risk-aware decision-making in healthcare supply chains
Executed complete ML workflows including data preprocessing, feature engineering, model training, evaluation, and cross-model comparison

Feedforward neural network to classify whether a person will subscribe to a particular program using behavioral and demographic features.

Regression model to predict vehicle emission levels (PPM), enabling data-driven environmental compliance and analysis.

Machine learning model to forecast interest rates based on historical financial and macroeconomic indicators.

Demand forecasting model for counterfeit medicine sales patterns to support risk-aware decision-making in healthcare supply chains.

Python Machine Learning Supervised Learning Classification Regression Neural Networks (FFN) Feature Engineering Model Evaluation Applied Data Science