基于Light GBM算法的游戏付费预测Game Payment Prediction Based on LightGBM Algorithm
卢厚达;李昕;褚治广;张秘源;
摘要(Abstract)：
针对游戏内玩家付费情况预测的问题，通过对数据集的清洗、降维以及数据分析，对游戏内玩家ID、在线时长以及7 d内的付费情况等特征数据的提取和分析，并预测玩家前45 d的付费情况，通过4种算法的对比分析得出Light GBM模型的预测结果更加准确、效率更高。
关键词(KeyWords)： 游戏付费预测;LightGBM;XGBoost
基金项目(Foundation):
作者(Authors): 卢厚达;李昕;褚治广;张秘源;
DOI: 10.15916/j.issn1674-3261.2022.05.004
参考文献(References)：
- [1] Newzoo Report, Global Games Market(2020)[Z]. https://newzoo. com/insights/articles/game-engagement-duringcovid-pandemic-adds-15-billion-to-global-games-market%20revenue-forecast/. Accessed 25 Feb 2021.
- [2] Michael G(2017)Mobile Revenue Forecasting:A Guide to Not Losing Your Shirt. https://www.gdcvault.com/play/1024470/Mobile Revenue Forecasting-A-Guide/. Accessed15 Jan 2021.
- [3] Davenport TH, Harris JG, Morison R(2010)Analytics at Work:Smarter Decisions, Better Results, 1st edn. Harvard Business Review Press, United states.
- [4] Kim J H, Gunn D V, Schuh E, Phillips B, Pagulayan RJ,Wixon D(2008)Tracking real-time user experience(TRUE):A compre-hensive instrumentation solution for complex systems[A]. In:SIGCHI conference on human factors in computing systems[C]. Florence, Italy:443–451.
- [5] Hullett K, Nagappan N, Schuh E, Hopson J(2011)Data analyt-ics for game development(NIER Track)[A]. In:33rd International Conference on Software Engineering[C].Waikiki, Honolulu, USA:940–943
- [6] Ke G, Meng Q, Finley T, et al. LightGBM:a highly efficient gradient boosting decision tree[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS'17). New York:Curran Associates Inc, Red Hook, 2018:3149.