Abstract
The game market is an increasingly large industry. The board-game market, which is the most traditional in the game market, continues to show a steady growth. It is very important for both publishers and players to predict the propensity of users in this huge market and to recommend new games. Despite its importance, no study has been performed on board-game recommendation systems. In this study, we propose a method to build a deep-learning-based recommendation system using large-scale user data of an online community related to board games. Our study showed that new games can be effectively recommended for board-game users based on user big data accumulated for a long time. This is the first study to propose a personalized recommendation system for users in the board-game market and to introduce a provision of new large datasets for board-game users. The proposed dataset shares symmetric characteristics with other datasets and has shown its ability to be applied to various recommendation systems through experiments. Therefore, the dataset and recommendation system proposed in this study are expected to be applied for various studies in the field.
Highlights
We evaluated the recommendation systems by various evaluation metrics, including precision@N, recall@N, mean average precision (MAP), normalized discounted cumulative gain (NDCG@N), and mean reciprocal rank (MRR) similar to the studies by in [7,8,14,28,43,44]
MAP is the mean of the average precision (AP) of all users in U, given rel ( N ) = 1 if the predicted N-th item in Ris the ground truth R when AP
We present a deep learning-based recommendation system using large-scale user data related to the board game
Summary
The game market is expanding because of advances in technology, platforms, and devices. The recent recommendation systems such as convolutional sequence embedding recommendation model (Caser) [7] and self-attentive sequential recommendation (SASRec) [8] use the interaction sequences that contain fruitful information about each user’s behavior [9], e.g., music listening, purchasing merchandise [10], watching YouTube [11], and playing video games [2], and the similarity between the items by capturing both long-range and short-range dependencies of user-item interaction sequences. John-K92/Recommendation-Systems-for-BoardGame-Platforms) to test whether recommendations can properly obtain sequential interactions in the board-game market from a large-scale dataset. Based on sequential recommendation studies [7,8,13,14], we hypothesize that solely feeding the models with item preference sequences of users is redundant to test recommendations in the board-game market. We provide the potential of sequential recommendations in the board-game platform
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
