A Power BI dashboard developed to analyze global video game sales, uncover market trends, and provide data-driven insights across regions, genres, and platforms.

This project aims to build a game recommendation system for Steam users using machine learning techniques. It utilizes a custom dataset of Steam IDs to retrieve user-specific information such as owned games, playtimes, and game tags through the Steam Web API. The collected data is then processed and used to train a machine learning model.

Identifying patterns that determine game success across global regions and platforms to inform retail strategies for 2017.

Exploratory Power BI analysis of gaming industry trends including revenue, players, genres, developers, platforms, and growth.

A distributed system that provides a service to store, retrieve, and analyse the game data of popular multiplayer online survival games such as CS: GO, PUBG, Fortnite, etc.

A powerful recommendation system for Steam games, combining Content-Based and Collaborative Filtering techniques. Built with Python, Scikit-learn, and Streamlit to deliver accurate, real-time game recommendations. Perfect for gamers and data scientists interested in building intelligent recommendation engines.

Cleaned and visualized 20K+ messy sales records for gaming products, building interactive dashboards in Tableau to reveal insights by product, region, and channel.

🕹️ Decoding the "Achiever" quest in PS4 gaming using Bartle’s Taxonomy. A behavioral analytics project transitioning from KNIME to Python, featuring Decision Tree models with 100% classification accuracy. 🧙‍♂️✨

Análisis prospectivo del mercado global de videojuegos (1980-2016). Implementación de EDA y pruebas de hipótesis para la optimización de inversión publicitaria mediante Python y estadística descriptiva.

EDA in R on Steam game data to analyze price distribution and its relationship with user reviews.

Explorer un dataset de 10 000 jeux vidéo populaires afin d’identifier les tendances clés de l’industrie. 🎮