perCLTV: A General System for Personalized Customer Lifetime Value Prediction in Online Games

Abstract

Online games make up the largest segment of the booming global game market, in terms of revenue as well as players. Unlike games that sell games at one time for profit, online games make money from in-game purchases by a large number of engaged players. Therefore, Customer Lifetime Value (CLTV) is particularly vital for game companies to improve marketing decisions and increase game revenues. Nowadays, as virtual game worlds are becoming increasingly innovative, complex, and diverse, the CLTV of massive players is highly personalized. That is, different players may have very different patterns of CLTV, especially on churn and payment. However, current solutions are inadequate in terms of personalization and thus limit predictive performance. First, most methods just attempt to address either task of CLTV, i.e., churn or payment, and only consider the personalization from one of them. Second, the correlation between churn and payment has not received enough attention and its personalization has not been fully explored yet. Last but not least, most solutions around this line are conducted based on historical data where the evaluation is not convincing enough without real-world tests. To tackle these problems, we propose a general system to predict personalized customer lifetime value in online games, named perCLTV. To be specific, we revisit the personalized CLTV prediction problem from the two sub-tasks of churn prediction and payment prediction in a sequential gated multi-task learning fashion. On this basis, we develop a generalized framework to model CLTV across games in distinct genres by heterogeneous player behavior data, including individual behavior sequential data and social behavior graph data. Comprehensive experiments on three real-world datasets validate the effectiveness and rationality of perCLTV, which significantly outperforms other baseline methods. Our work has been implemented and deployed in many online games released from NetEase Games. Online A/B testing in production shows that perCLTV achieves a prominent improvement in two precision marketing applications of popup recommendation and churn intervention.

Match experiences affect interest: Impacts of matchmaking and performance on churn in a competitive game

“…We attempted to measure players' dedication to the game by their playing frequencies, real money paid, and in-game monetary transactions. These features are highly correlated with churn, and this correlation has been verified many times in several churn prediction studies [18] , [38] , [32] , [52] . Play count : The total number of matches played per day.…”

“…In most churn prediction studies, session-related features, such as the number of logins, playtime, and the average time between games, were utilized as critical features that could indicate the extent to which players were engaged in a game [18] , [10] . Further studies added features of different kinds, such as social activities [25] , [31] , achievements [8] , and payments [51] , [52] . Most of the studies rely on machine learning-based approaches to deal with large and complex datasets.…”

Ecampus's Role in Supporting Learning in Higher Education

“…One can learn that e-campus is the right choice for use in today's technological age (Hopkinson et al, 2018;Roy et al, 2018). Many types of online learning media can be chosen by educators to provide convenience in the teaching and learning process (Ilyas et al, 2023;Zhao et al, 2023). In this all-digital era, students should be given learning that can increase their interest and motivation to learn (Lee et al, 2021;Posever et al, 2021).…”