Frida Putriassa
TABLETOP GAME RECOMMENDATION SYSTEM (ITEM-BASED COLLABORATIVE FILTERING USING PYTHON)
I've created a smart system using Item-Based Collaborative Filtering. It looks at the games you and others liked and suggests new tabletop games that match your interests. It's like having a game buddy who knows exactly what you'd enjoy!
A tabletop game recommendation system enhances gaming with personalized suggestions, saving time, fostering community engagement, and uncovering hidden gems, contributing to a vibrant gaming community.
-----
Collaborative filtering is a recommendation technique that predicts user preferences by leveraging the collective behavior and preferences of a group of users. It can be user-based, where recommendations are based on similarities between users, or item-based, where recommendations are made by identifying similarities between items.
Item-based filtering, also known as content-based filtering, is a recommendation method that suggests items similar to those a user has liked or interacted with in the past. It focuses on the attributes or features of items and recommends others with similar characteristics.
Table of Content :
Link : Youtube | Google Colab | Dataset
TABLETOP GAME RECOMMENDATION SYSTEM BY FRIDA PUTRIASSA.
ABOUT DATASET
This dataset Feature-rich multi-table dataset full of interesting information about Board Games which can be used for tasks such as exploratory EDA, predictive modeling, or recommender systems. This data set includes nine potential files for exploration and/or modeling :
The dataset used in this recommendation system is the last dataset, dataset user_ratings, that has all ratings for all game id with username. There are over 441k unique users and ~19 million ratings.
PREPROCESSING
USER TO USER COLLABORATIVE FILTERING
GAME TO GAME COLLABORATIVE FILTERING
CONCLUSION
In conclusion, our exploration of an item-based collaborative filtering recommendation system for tabletop games signifies a significant step forward in optimizing the gaming experience. By strategically utilizing included user ratings, we've harnessed valuable insights to develop a powerful recommender system, capable of offering tailored suggestions based on both individual preferences and collective gaming behaviors.
-----------------------------------------------------------------------------------------
Youtube Video :