ABSTRACT
Recommendation in outcome based platforms (eg. skill gaming, financial trading) where users get rewards based on their choices and the subsequent non-deterministic outcomes from such choices presents a unique set of challenges. Unlike other online services (e.g., e-commerce, social media), these platforms often see: (a) distinctive longitudinal behavior patterns in users’ transactions, (b) enormous content generated by the user interactions, (c) a dynamic interplay between the users’ transactional history and outcomes towards their future behavior, (d) ordinal nature of transaction elements. Motivated by these observations, we propose ComParE (Competing Parallel Networks with Expert Network), a novel personalized recommendation framework that: (i) exploits the distinct behavioral trends in the data, by training competing parallel networks as local experts, (ii) trains a global expert network to get the overall picture for the final prediction, and (iii) introduces custom loss functions to learn inherent ordering and interpretations of the classes being predicted. With the example of personalizing entry fee choices for the game of Rummy on the RummyCircle platform we show: (i) distinct and robust user Personas found based on historical entry fee selections; (ii) significant boosts in the entry fee predictions through ComParE with both neural networks and classical ML algorithms for local and global experts; (iii) substantial lifts over platform default as shown through offline analysis. ComParE significantly outperforms other baselines including well known deep learning models, as shown through offline experiments.
- Fabian Abel, Qi Gao, Geert-Jan Houben, and Ke Tao. 2011. Analyzing temporal dynamics in twitter profiles for personalized recommendations in the social web. In Proceedings of the 3rd international web science conference. 1–8.Google ScholarDigital Library
- Sercan O Arik and Tomas Pfister. 2019. Tabnet: Attentive interpretable tabular learning. arXiv preprint arXiv:1908.07442(2019).Google Scholar
- Giuliano Arru, Davide Feltoni Gurini, Fabio Gasparetti, Alessandro Micarelli, and Giuseppe Sansonetti. 2013. Signal-based user recommendation on twitter. In Proceedings of the 22nd International Conference on World Wide Web. 941–944.Google ScholarDigital Library
- Joydeep Banerjee, Gurulingesh Raravi, Manoj Gupta, Sindhu K Ernala, Shruti Kunde, and Koustuv Dasgupta. 2016. CAPReS: Context Aware Persona Based Recommendation for Shoppers.. In AAAI. 680–686.Google Scholar
- Oren Barkan, Yonatan Fuchs, Avi Caciularu, and Noam Koenigstein. 2020. Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering. In Fourteenth ACM Conference on Recommender Systems. 468–473.Google ScholarDigital Library
- Anand Bodas, Bhargav Upadhyay, Chetan Nadiger, and Sherine Abdelhak. 2018. Reinforcement learning for game personalization on edge devices. In 2018 International Conference on Information and Computer Technologies (ICICT). IEEE, 119–122.Google ScholarCross Ref
- Elizabeth A Boyle, Thomas M Connolly, Thomas Hainey, and James M Boyle. 2012. Engagement in digital entertainment games: A systematic review. Computers in human behavior 28, 3 (2012), 771–780.Google Scholar
- Donghui Cho. 2015. What influences people to purchase ingame mobile items?: Analysis of motivational drivers to use ingame mobile game items in the US. Michigan State University.Google Scholar
- Evangelia Christakopoulou and George Karypis. 2016. Local item-item models for top-n recommendation. In Proceedings of the 10th ACM Conference on Recommender Systems. 67–74.Google ScholarDigital Library
- Juho Hamari and Lauri Keronen. 2017. Why do people buy virtual goods: A meta-analysis. Computers in Human Behavior 71 (2017), 59–69.Google ScholarDigital Library
- Stephen Karpinskyj, Fabio Zambetta, and Lawrence Cavedon. 2014. Video game personalisation techniques: A comprehensive survey. Entertainment Computing 5, 4 (2014), 211–218.Google ScholarCross Ref
- Guolin Ke, Jia Zhang, Zhenhui Xu, Jiang Bian, and Tie-Yan Liu. 2018. TabNN: A Universal Neural Network Solution for Tabular Data. (2018).Google Scholar
- Piji Li, Zihao Wang, Lidong Bing, and Wai Lam. 2019. Persona-Aware Tips Generation. In The World Wide Web Conference. 1006–1016.Google Scholar
- Holin Lin and Chuen-Tsai Sun. 2007. Cash trade within the magic circle: free-to-play game challenges and massively multiplayer online game player responses.. In DiGRA Conference.Google Scholar
- Enrica Loria and Annapaola Marconi. 2018. Player Types and player behaviors: analyzing correlations in an on-the-field gamified system. In Proceedings of the 2018 Annual Symposium on Computer-Human Interaction in Play Companion Extended Abstracts. 531–538.Google ScholarDigital Library
- Ding-Bang Luh, Elena Carolina Li, and Chia-Chen Dai. 2016. Game factors influencing players to continue playing online pets. IEEE Transactions on Computational Intelligence and AI in Games 9, 3(2016), 267–276.Google ScholarCross Ref
- Ben Marder, David Gattig, Emily Collins, Leyland Pitt, Jan Kietzmann, and Antonia Erz. 2019. The Avatar’s new clothes: Understanding why players purchase non-functional items in free-to-play games. Computers in Human Behavior 91 (2019), 72–83.Google ScholarCross Ref
- Xia Ning and George Karypis. 2011. Slim: Sparse linear methods for top-n recommender systems. In 2011 IEEE 11th International Conference on Data Mining. IEEE, 497–506.Google ScholarDigital Library
- Genaína Nunes Rodrigues, Carlos Joel Tavares, Naiara Watanabe, Carina Alves, and Raian Ali. 2018. A persona-based modelling for contextual requirements. In International Working Conference on Requirements Engineering: Foundation for Software Quality. Springer, 352–368.Google ScholarCross Ref
- Joni Salminen, Bernard J Jansen, Jisun An, Haewoon Kwak, and Soon-Gyo Jung. 2019. Automatic persona generation for online content creators: Conceptual rationale and a research agenda. In Personas-User focused design. Springer, 135–160.Google Scholar
- Joni Salminen, Jukka Vahlo, Aki Koponen, Soon-Gyo Jung, Shammur A Chowdhury, and Bernard J Jansen. 2020. Designing Prototype Player Personas from a Game Preference Survey. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1–8.Google ScholarDigital Library
- Valentino Servizi, Sokol Kosta, Allan Hammershøj, and Henning Olesen. 2018. A User Experience Model for Privacy and Context Aware Over-the-Top (OTT) TV Recommendations.. In CIKM Workshops.Google Scholar
- Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, and Aditya Nori. 2019. Adaptive neural trees. In International Conference on Machine Learning. PMLR, 6166–6175.Google Scholar
- Selen Turkay and Sonam Adinolf. 2015. The effects of customization on motivation in an extended study with a massively multiplayer online roleplaying game. Cyberpsychology: Journal of Psychosocial Research on Cyberspace 9, 3(2015).Google Scholar
- Daniel Gallego Vico, Gabriel Huecas, and J Salvachúa Rodríguez. 2012. Generating context-aware recommendations using banking data in a mobile recommender system. In ICDS 2012, The Sixth International Conference on Digital Society. 73–78.Google Scholar
- Su Xue, Meng Wu, John Kolen, Navid Aghdaie, and Kazi A Zaman. 2017. Dynamic difficulty adjustment for maximized engagement in digital games. In Proceedings of the 26th International Conference on World Wide Web Companion. 465–471.Google ScholarDigital Library
- Jinsung Yoon, James Jordon, and Mihaela van der Schaar. 2018. INVASE: Instance-wise variable selection using neural networks. In International Conference on Learning Representations.Google Scholar
- Chang Zhou, Jinze Bai, Junshuai Song, Xiaofei Liu, Zhengchao Zhao, Xiusi Chen, and Jun Gao. 2017. Atrank: An attention-based user behavior modeling framework for recommendation. arXiv preprint arXiv:1711.06632(2017).Google Scholar
Index Terms
- ComParE: A User Behavior Centric Framework for Personalized Recommendations in Skill Gaming Platforms
Recommendations
Aspect Based Recommendations: Recommending Items with the Most Valuable Aspects Based on User Reviews
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn this paper, we propose a recommendation technique that not only can recommend items of interest to the user as traditional recommendation systems do but also specific aspects of consumption of the items to further enhance the user experience with ...
User Similarity Adjustment for Improved Recommendations
MIKE 2015: Proceedings of the Third International Conference on Mining Intelligence and Knowledge Exploration - Volume 9468Recommender systems are becoming more and more attractive in both research and commercial communities due to Information overload problem and the popularity of the Internet applications. Collaborative Filtering, a popular branch of recommendation ...
Revisiting tendency based collaborative filtering for personalized recommendations
CODS-COMAD '18: Proceedings of the ACM India Joint International Conference on Data Science and Management of DataRecommender systems alleviates the problem of information overload by providing personalized suggestions to the users. In this context, recently introduced tendency based recommendation technique is proven to be more simple, intuitive and accurate than ...
Comments