Predictive modeling for early success forecasting of movies using Video-On-Demand streaming data, featuring Gradient Boosting Machines and advanced feature engineering techniques.

An end-to-end data analytics and forecasting project analyzing YouTube series performance, audience retention, engagement trends, and geographic distribution to predict future growth and optimize content strategy.

An interactive data analytics dashboard built to analyze content distribution, ratings, genres, and trends on Prime Video.

Content ROI and Genre Profitability is a data analytics project focused on evaluating content performance across different Genres and Platforms using financial and engagement metrics

Comprehensive SQL analysis of Netflix content library with 15 advanced queries exploring movies vs TV shows, ratings, genres, directors, actors, and regional content distribution.

Power BI dashboard analyzing 3.4K+ web series (2000–2024) across 42 countries, 96 industries, and 70M+ votes.

A machine learning project that predicts movie success in two ways: financial blockbusters (top 25% by revenue) and popularity blockbusters (top 25% by audience score). It compares multiple models to understand what drives each type of success.

This repository provides a comprehensive Exploratory Data Analysis (EDA) of entertainment content, revealing trends in relation to audience preferences, production locations, release patterns and content duration.

A comprehensive Power BI dashboard providing analytical insights into movie industry data including box office performance, ratings, genres, director/actor metrics, and trends. Analyzes budget vs revenue, release timing impact, and audience preferences.

Predictive analysis of Japanese media IP to optimise global market expansion.

Find out what's TikTok algorithm to post and get more viewers

Machine learning pipeline for predicting movie box office success. Includes web scraping, data pipelines, feature engineering, ML models, MLflow tracking, and a web interface for predictions.