Optimized media, analytics and graphics software stack images. Use the dockerfile(s) in your project or as a recipe book for bare metal installation.

The shared repository for Media Cloud web apps (Explorer, Source Manager, Topic Mapper)

Code that drives the public web-based tools for the Media Cloud Online News Archive and Directory.

Predicting online news popularity using New York Times articles in 2020

Mapped 6,874 titles across 37 genres to reveal 43% of catalogue targets U/A 13+ — uncovering an underserved kids and family content gap

This repository contains a project that analyzes the impact of media advertising 📺📻📰 on sales 💸 using SQL for data processing and Tableau for interactive dashboards 📊. The dashboard visualizes how advertising spend influences sales and helps optimize marketing ROI 📈.

This project focuses on Quarterly Revenue Forecasting across three media platforms.

End-to-end OTT streaming analytics — viewership KPIs (DAU, MAU, ARPU, churn), content performance, revenue attribution & churn prediction using Python, SQL, Scikit-learn

ProMedia Insight Hub is an AI-powered media analytics dashboard for managing, analyzing, and extracting strategic insights from news data in a modern and efficient way.

Google News data extraction tool

Interactive JioHotstar Content Analytics Dashboard built with Power BI, Python, Numpy, Pandas, Plotly, Pillow, and Streamlit, featuring content trends, genre analysis, ratings insights, and global distribution analytics.

Movie market trend analysis using Apache PySpark and Databricks — revenue patterns, genre performance, and ratings across 1000 IMDB films (2006–2016)

End-to-end PR Intelligence Dashboard built using Power BI to analyze media coverage, brand performance, competitor activity, and actionable business insights.

Jupyter Notebook dedicated to the detailed analysis of the Netflix movies and tv shows using the R programming language

Real-time analytics pipeline: Kafka → Spark Streaming → Delta Lake (MinIO) + ClickHouse. Includes ML models for churn, recommendations, and conversion prediction. Production-ready with CI/CD, data governance, and terabyte-scale architecture.

news extraction automation tool

Streaming algorithms suffer from "Blockbuster Bias"—they push expensive hits while high-quality content gets buried.

Exploratory data analysis of Netflix's global content library — uncovering content distribution trends, genre preferences, audience ratings, and growth patterns across 6,000+ titles using Python and Tableau

Personal media intelligence dashboard. React + Recharts + Vite. Analyzes viewing patterns across film and TV with genre breakdowns, year-over-year trends, and discovery heatmaps.

End-to-end research dashboard measuring shifts in public attention and sentiment around the YSL trial, with a focus on ThuggerDaily’s temporal alignment with major legal events