网络游戏案例研究: 用户行为分析和流失预测过

用户流失预测在很多领域得到关注,目前主流的用户流失预测方法是使用分类法。网络游戏领域发展迅猛,但用户特征选取、特征处理和流失预测的相关研究较少。本文以一款网页网络游戏的用户记录为数据,对用户游戏行为进行分析对比,发现流失用户在游戏投入、博彩热情、玩家互动方面与正常用户存在显著差异;同时发现网络游戏数据存在样本分布不平衡、候选特征库庞大和干扰差异多等难点。在此分析基础上,本文探讨了网游用户的关键特征提取的关注方向,以及归一化和对齐化在特征处理中的关键作用。实验表明,本文提取的特征具有很好的区分度。

Abstract

The task of user churn prediction is a research issue in many fields. Currently the available solution usually built uopna classification models. For the online games which is developing rapidly, the churn prediction is not well addressed yet. This paper chooses certain online game user logs and analyzed user behaviors, finding significant differences in game investment, interests in lottery and player interaction between churn users and normal users. This paper also suggests that there are such challenges in online game data processing as the unbalanced data, the huge candidate features, the interference differences and so on. This paper also discusses the direction when selecting features, as well as the key role of normalization and alignment in feature processing. Experiments prove that the features selected by this paper are informative.

关键词

行为分析 /特征提取 /流失预测 /网络游戏
{{custom_keyword}} /

Key words

behavior analysis / feature selection / churn prediction / online games{{custom_keyword}} /

过岩巍,吴悦昕,赵 鑫,闫宏飞,黄建兴.网络游戏案例研究: 用户行为分析和流失预测过. 中文信息学报. 2016, 30(1): 183-190

GUO Yanwei, WU Yuexin, ZHAO Xin, YAN Hongfei, HUANG Jianxing.User Behavior Analysis and Churn Prediction: A Case Study on Online Games. Journal of Chinese Information Processing. 2016, 30(1): 183-190

参考文献

[1] 夏国恩, 金炜东. 基于支持向量机的客户流失预测模型[J]. 系统工程理论与实践, 2008, 28(1): 71-77.
[2] 应维云, 覃正, 赵宇, 等. SVM 方法及其在客户流失预测中的应用研究[J]. 系统工程理论与实践, 2007, 27(7): 105-110.
[3] 朱帮助, 张秋菊. 电子商务客户流失三阶段预测模型[J]. 中国软科学, 2010 (006): 186-192.
[4] Xie Y, Li X, Ngai E W T, et al. Customer churn prediction using improved balanced random forests[J]. Expert Systems with Applications, 2009, 36(3): 5445-5449.
[5] Morik K, Kpcke H. Analysing customer churn in insurance data-a case study[M].Knowledge Discovery in Databases: PKDD 2004. Springer Berlin Heidelberg, 2004: 325-336.
[6] Nie G, Wang G, Zhang P, et al. Finding the hidden pattern of credit card holders churn: A case of China[M].Computational Science-ICCS 2009. Springer Berlin Heidelberg, 2009: 561-569.
[7] 颜昌沁, 胡建华, 周海河. 基于 Clementine 神经网络的电信客户流失模型应用[J]. 电脑应用技术, 2009 (1): 7-12.
[8] Tsai C F, Lu Y H. Customer churn prediction by hybrid neural networks[J]. Expert Systems with Applications, 2009, 36(10): 12547-12553.
[9] Hung S Y, Yen D C, Wang H Y. Applying data mining to telecom churn management[J]. Expert Systems with Applications, 2006, 31(3): 515-524.
[10] Liu Y, Kalagnanam J R, Johnsen O. Learning dynamic temporal graphs for oil-production equipment monitoring system[C]//Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 2009: 1225-1234.
[11] Cheng H, Tan P N. Semi-supervised learning with data calibration for long-term time series forecasting[C]//Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 2008: 133-141.
[12] 李航. 统计学习方法[M]. 第1版, 北京:清华大学出版社, 2012: 60-63.
[13] Chen S, Cowan C F N, Grant P M. Orthogonal least squares learning algorithm for radial basis function networks[J]. Neural Networks, IEEE Transactions on, 1991, 2(2): 302-309.
[14] Laurikkala J. Improving identification of difficult small classes by balancing class distribution[M]. Springer Berlin Heidelberg, 2001: 63-66.
[15] Estabrooks A, Jo T, Japkowicz N. A multiple resampling method for learning from imbalanced data sets[J]. Computational Intelligence, 2004, 20(1): 18-36.
[16] Elkan C. The foundations of cost-sensitive learning[C]//Proceedings of the International joint conference on artificial intelligence. LAWRENCE ERLBAUM ASSOCIATES LTD, 2001, 17(1): 973-978.
[17] Croft W B, Metzler D, Strohman T. Search engines: Information retrieval in practice[M].第1版, 北京: 北京机械工业出版社, 2009. 308-313.
[18] 朱世武, 崔嵬, 谢邦昌. 移动电话客户流失数据挖掘[J]. 数理统计与管理, 2005, 24(1): 62-69.
[19] Borbora Z, Srivastava J, Hsu K W, et al. Churn Prediction in MMORPGs using Player Motivation Theories and an Ensemble Approach[C]//Proceedings of the 2011 ieee third international conference on social computing (socialcom). IEEE, 2011: 157-164.

{{custom_fnGroup.title_cn}}

脚注

基金

国家自然科学基金(U1536201,61272340);江苏未来网络创新研究院项目(BY2013095-4-02)

相关知识

用户行为研究（一）：目标用户调研
腾讯移动游戏用户研究大揭秘：研究思路、方法、案例及步骤 – 人人都是产品经理,
游戏直播用户使用行为研究
网络游戏用户流失原因分析
青少年网络游戏问题行为的文化、社会、个体三因素分析
网络游戏外挂行为定罪分析——以典型刑事类案为样本
网易网络游戏营销策略研究+PEST+SWOT分析
移动网络游戏产业的发展现状和用户付费情况分析、发展前景预测
移动游戏monetization策略和用户分析.pptx
网络游戏用户与用户付费数据分析