My Work

End-to-end machine learning projects. Each case study includes the problem context, architecture decisions, trade-offs, and results.

Featured Work

End-to-end machine learning projects demonstrating data analysis, model development, and real-world problem solving.

CompletedApril 2025 – May 2025

Customer Churn Prediction System

Classification & Business Analytics

End-to-end ML system to predict customer churn and identify business risks

  • Analyzed customer behavior data to identify churn patterns and business risks
  • Preprocessed large datasets by handling missing values and categorical variables
  • Built Logistic Regression and Random Forest models for churn prediction
PythonPandasScikit-learnEDAMatplotlib
CompletedJanuary 2025 – March 2025

House Price Prediction System

Machine Learning Regression

End-to-end ML pipeline to predict house prices using real-world datasets

  • Built end-to-end machine learning pipeline for house price prediction
  • Performed data cleaning, feature engineering, and exploratory data analysis
  • Implemented Linear Regression and Random Forest models with comparison
PythonPandasNumPyScikit-learnMatplotlib
CompletedJune 2025 – July 2025

Handwritten Digit Recognition

Deep Learning Computer Vision

CNN-based system for classifying handwritten digits using MNIST dataset

  • Designed and trained a Convolutional Neural Network (CNN) for digit classification
  • Used MNIST dataset (70,000 images) for training and validation
  • Achieved high classification accuracy through model optimization
PythonTensorFlowPyTorchCNNNumPy