Churn prediction for high-value players in casual social games

Runge, Julian; Gao, Peng; Garcin, Florent; Faltings, Boi

doi:10.1109/cig.2014.6932875

Cited by 118 publications

(129 citation statements)

References 7 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…And we finally add deep multilayer perceptrons (Deep-MLP) to the mix because of their recent superiority in a number of applications [28,29]. [2] further find them to perform well for user behavior prediction in freemium games. [4,9,30,31] all highlight the relevance of social interaction for engagement, monetization and virality in freemium games and products more generally.…”

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

“…E.g. [2,[18][19][20][21] investigate the prediction of player disengagement/churn, [22][23][24] focus on player retention and [1] predict players' purchase decisions in mobile free-to-play games. Player engagement and purchasing are at the core of players' value to a company, and so is their combined outcome: Monetary LTV.…”

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

“…These users contribute the majority of overall revenue -e.g. the top 10% of paying users in [2] contribute 60% of revenue -and hence 'co-finance' product use and the development of future products for all other users [4] 1 . Figures 1 and 2 visualize this phenomenon for the freemium setting under study in this paper, where we observe that more than 80 % of the revenue comes from 20 % of premium users.…”

Section: Introductionmentioning

confidence: 99%

“…users with high predicted LTV, can be offered preferential treatment by customer service agents to ensure a great product experience or they can be enrolled in loyalty programs and other tailored marketing initiatives [2].…”

Section: Introductionmentioning

confidence: 99%

“…Tinder, extend their contractual upgrades with ad-hoc, non-contractual premium offers that allow for repeat purchasing at the customers' discretion. Purely non-contractual freemium models are common in products with large network effects such as Skype, many dating and lifestyle apps, and in digital (free-to-play) games [1][2][3]. Non-contractual upgrades are usually made in in-app purchases (IAPs) and often referred to as micro-transactions as they tend to be made in small amounts and repeated manifold by engaged players [1].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Sifa¹,

Runge²,

Bauckhage³

et al. 2018

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

In non-contractual freemium and sharing economy settings, a small share of users often drives the largest part of revenue for firms and co-finances the free provision of the product or service to a large number of users. Successfully retaining and upselling such high-value users can be crucial to firms' survival. Predictions of customers' Lifetime Value (LTV) are a much used tool to identify high-value users and inform marketing initiatives. This paper frames the related prediction problem and applies a number of common machine learning methods for the prediction of individual-level LTV. As only a small subset of users ever makes a purchase, data are highly imbalanced. The study therefore combines said methods with synthetic minority oversampling (SMOTE) in an attempt to achieve better prediction performance. Results indicate that data augmentation with SMOTE improves prediction performance for premium and high-value users, especially when used in combination with deep neural networks.

show abstract

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Sifa¹,

Runge²,

Bauckhage³

et al. 2018

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

Game Analytics on Free to Play

Flunger

Mladenow

Strauß

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Identifying Influences of Game Upgrades on Profitable Players Behavior in MMORPGs

Kummer

Iida

Nievola

et al. 2019

Entertainment Computing and Serious Games

View full text Add to dashboard Cite

Players can change their interest in continuing playing due to many reasons, such as the game content available to them. Therefore, game upgrades play an important role as they have the potential to influence players, being it a "double-edged sword", as players may like the new challenges or not. Among the active players, "whales" are those players that are the most profitable ones. The goal of this paper is to answer the following research question: "What are the influences of game upgrades on profitable players behavior?". To do that, we propose to apply and jointly interpret the results of four metrics (or KPIs): Commitment, Key Risk Indicator, Available Motivational Growth, and Game Refinement Value. This approach was applied to an MMORPG dataset that contains four kinds of upgrades. As results, the proposed joining identified three key influences and two players aspects, showing the potential to be used by game producers to evaluate the acceptance and influences of their upgrades in real situations.

show abstract

Churn prediction for high-value players in casual social games

Cited by 118 publications

References 7 publications

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Game Analytics on Free to Play

Identifying Influences of Game Upgrades on Profitable Players Behavior in MMORPGs

Contact Info

Product

Resources

About