GAMEPICK
Game recommendation platform that analyzes user behavior to suggest personalized game choices.
Data Engineer
Built a data-driven game recommendation system using real user activity data.
GAMEPICK was developed at Hack Košice 2022 as a full-stack application designed to recommend video games based on user behavior and preferences. The goal was to combine a user-friendly frontend with a data-driven backend capable of analyzing large datasets.
The platform processes user activity data to generate personalized game recommendations. The backend leverages Python, Pandas, and NumPy within a Jupyter Notebook environment to analyze and transform data into meaningful insights used for recommendation logic.
One of the main challenges was working with unfamiliar tools such as Pandas and Jupyter in a time-constrained hackathon setting, as well as handling and structuring larger datasets effectively. This required rapid learning and adaptation to data analysis workflows.
The project emphasized the importance of data preprocessing and analysis in building recommendation systems, and demonstrated how cloud infrastructure can be used to support scalable backend processing.
GAMEPICK highlights early experience with data-driven application design, combining frontend usability with backend analytics to deliver a practical recommendation engine.
Contribution
Developed backend data processing pipelines using Python, Pandas, and NumPy, set up the Google Cloud environment, and worked with real-world user data to build the recommendation system.
