Projects

This project provides an analysis tool for WhatsApp chat logs, which extracts essential information such as frequently used words, active users, and chat patterns to provide a comprehensive understanding of the chat history.

The recommendation system for anime shows/movies employs ML algorithms, NLP techniques, collaborative filtering and cosine similarity to provide personalized recommendations based on users’ viewing history or preferences, utilizing tags for genre, type, studio, director, crew, episodes, and writer.

Developed a spam classifier to filter out spam messages using various techniques such as tokenization and machine learning algorithms including Naive Bayes, Random Forest, K-Nearest Neighbors, and Support Vector Machines. The Random Forest algorithm achieved the best performance with an F1-score of 0.9.

A machine learning-based Amazon Ad Tag Bidding Price Predictor tool was developed and demonstrated its ability to improve the performance of advertising campaigns with 0.992 R2 score accuracy.

A customer churn prediction model developed using machine learning techniques with 0.91 accuracy, precision, recall, and f1 score, showcasing expertise in data analysis and ML to deliver insights to improve customer retention.