Chuhan Wu
ABSTRACT
The ultimate goal of recommender systems is satisfying users’ information needs in the long term. Despite the success of current recommendation techniques in targeting user interest, optimizing long-term user engagement and platform revenue is still challenging due to the restriction of optimization objectives such as clicks, ratings, and dwell time. Customer lifetime value (LTV) reflects the total monetary value of a customer to a business over the course of their relationship. Accurate LTV prediction can guide personalized service providers to optimize their marketing, sales, and service strategies to maximize customer retention, satisfaction, and profitability. However, the extreme sparsity, volatility, and randomness of consumption behaviors make LTV prediction rather intricate and challenging. In this tutorial, we give a detailed introduction to the key technologies and problems in LTV prediction. We present a systematic technique chronicle of LTV prediction over decades, including probabilistic models, traditional machine learning methods, and deep learning techniques. Based on this overview, we introduce several critical challenges in algorithm design, performance evaluation and system deployment from an industrial perspective, from which we derive potential directions for future exploration. From this tutorial, the RecSys community can gain a better understanding of the unique characteristics and challenges of LTV prediction, and it may serve as a catalyst to shift the focus of recommender systems from short-term targets to long-term ones.
- Umair Akram, Peng Hui, Muhammad Kaleem Khan, Yasir Tanveer, Khalid Mehmood, and Wasim Ahmad. 2018. How website quality affects online impulse buying: Moderating effects of sales promotion and credit card use. Asia Pacific Journal of Marketing and Logistics (2018).Google Scholar
Cross Ref
- Josef Bauer and Dietmar Jannach. 2021. Improved Customer Lifetime Value Prediction With Sequence-To-Sequence Learning and Feature-Based Models. TKDD 15, 5 (2021), 1–37.Google ScholarDigital Library
- Paolo Burelli. 2019. Predicting customer lifetime value in free-to-play games. In Data analytics applications in gaming and entertainment. Auerbach Publications, 79–107.Google Scholar
- Pei Pei Chen, Anna Guitart, Ana Fernández del Río, and Africa Periánez. 2018. Customer lifetime value in video games using deep learning and parametric models. In Big Data. IEEE, 2134–2140.Google Scholar
- Ana Fernández del Río, Pei Pei Chen, and Africa Periánez. 2019. Profiling players with engagement predictions. In CoG. IEEE, 1–4.Google Scholar
- Anders Drachen, Mari Pastor, Aron Liu, Dylan Jack Fontaine, Yuan Chang, Julian Runge, Rafet Sifa, and Diego Klabjan. 2018. To be or not to be...social: incorporating simple social features in mobile game customer lifetime value predictions. In ACSW. ACM, 40:1–40:10.Google Scholar
- Peter S Fader, Bruce GS Hardie, and Ka Lok Lee. 2005. RFM and CLV: Using iso-value curves for customer base analysis. JMR 42, 4 (2005), 415–430.Google Scholar
- Sunil Gupta, Dominique Hanssens, Bruce Hardie, Wiliam Kahn, V Kumar, Nathaniel Lin, Nalini Ravishanker, and S Sriram. 2006. Modeling customer lifetime value. Journal of service research 9, 2 (2006), 139–155.Google ScholarCross Ref
- Junxiang Jiang. 2020. A Study of Game Payment Data Mining: Predicting High-Value Users for MMORPGs. In PAKDD Workshops. Springer, 181–192.Google ScholarDigital Library
- V Kumar, Girish Ramani, and Timothy Bohling. 2004. Customer lifetime value approaches and best practice applications. Journal of interactive Marketing 18, 3 (2004), 60–72.Google ScholarCross Ref
- Kunpeng Li, Guangcui Shao, Naijun Yang, Xiao Fang, and Yang Song. 2022. Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou. In CIKM. ACM, 3243–3251.Google Scholar
- Sahar F Sabbeh. 2018. Machine-learning techniques for customer retention: A comparative study. IJACSA 9, 2 (2018).Google Scholar
- Ahmet Tezcan Tekin, Tolga Kaya, and Ferhan Cebi. 2022. Customer lifetime value prediction for gaming industry: fuzzy clustering based approach. Journal of Intelligent & Fuzzy Systems 42, 1 (2022), 87–96.Google ScholarDigital Library
- Yegor Tkachenko. 2015. Autonomous CRM control via CLV approximation with deep reinforcement learning in discrete and continuous action space. arXiv preprint arXiv:1504.01840 (2015).Google Scholar
- Ali Vanderveld, Addhyan Pandey, Angela Han, and Rajesh Parekh. 2016. An Engagement-Based Customer Lifetime Value System for E-commerce. In KDD. ACM, 293–302.Google Scholar
- Xiaojing Wang, Tianqi Liu, and Jingang Miao. 2019. A deep probabilistic model for customer lifetime value prediction. arXiv:1912.07753 (2019).Google Scholar
- Yuhao Wang, Ha Tsz Lam, Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang. 2023. Multi-Task Deep Recommender Systems: A Survey. arXiv:2302.03525 (2023).Google Scholar
- Chuhan Wu, Jingjie Li, Qinglin Jia, Hong Zhu, Yuan Fang, and Ruiming Tang. 2023. Contrastive Multi-view Framework for Customer Lifetime Value Prediction. arXiv preprint arXiv:2306.14400 (2023).Google Scholar
- Mingzhe Xing, Shuqing Bian, Wayne Xin Zhao, Zhen Xiao, Xinji Luo, Cunxiang Yin, Jing Cai, and Yancheng He. 2021. Learning Reliable User Representations from Volatile and Sparse Data to Accurately Predict Customer Lifetime Value. In KDD. 3806–3816.Google Scholar
- Shiwei Zhao, Runze Wu, Jianrong Tao, Manhu Qu, Minghao Zhao, Changjie Fan, and Hongke Zhao. 2023. perCLTV: A general system for personalized customer lifetime value prediction in online games. TOIS 41, 1 (2023), 1–29.Google ScholarDigital Library
Recommendations
Customer Lifetime Value Measurement
The measurement of customer lifetime value is important because it is used as a metric in evaluating decisions in the context of customer relationship management. For a firm, it is important to form some expectations as to the lifetime value of each ...
Recommender System Rethink: Implications for an Electronic Marketplace with Competing Manufacturers
Recommender systems that inform consumers about their likely ideal products have become the cornerstone of e-commerce platforms that sell products from competing manufacturers. Using a model of an electronic marketplace in which two competing ...
Dynamic customer lifetime value prediction using longitudinal data: An improved multiple kernel SVR approach
Customer lifetime value (CLV), as an important metric in customer relationship management (CRM), has attracted widespread attention over the last decade. Most CLV prediction models do not take into consideration the dynamics of the customer purchase ...
Comments