当前位置: X-MOL 学术Expert Syst. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-objective Grammatical Evolution of Decision Trees for Mobile Marketing user conversion prediction
Expert Systems with Applications ( IF 7.5 ) Pub Date : 2020-11-20 , DOI: 10.1016/j.eswa.2020.114287
Pedro José Pereira , Paulo Cortez , Rui Mendes

The worldwide adoption of mobile devices is raising the value of Mobile Performance Marketing, which is supported by Demand-Side Platforms (DSP) that match mobile users to advertisements. In these markets, monetary compensation only occurs when there is a user conversion. Thus, a key DSP issue is the design of a data-driven model to predict user conversion. To handle this nontrivial task, we propose a novel Multi-objective Optimization (MO) approach to evolve Decision Trees (DT) using a Grammatical Evolution (GE), under two main variants: a pure GE method (MGEDT) and a GE with Lamarckian Evolution (MGEDTL). Both variants evolve variable-length DTs and perform a simultaneous optimization of the predictive performance and model complexity. To handle big data, the GE methods include a training sampling and parallelism evaluation mechanism. The algorithms were applied to a recent database with around 6 million records from a real-world DSP. Using a realistic Rolling Window (RW) validation, the two GE variants were compared with a standard DT algorithm (CART), a Random Forest and a state-of-the-art Deep Learning (DL) model. Competitive results were obtained by the GE methods, which present affordable training times and very fast predictive response times.



中文翻译:

移动营销用户转化预测的决策树多目标语法演变

移动设备在全球范围内的采用正在提高移动性能营销的价值,这得益于将移动用户与广告匹配的需求方平台(DSP)的支持。在这些市场中,仅当有用户转换时才发生货币补偿。因此,一个关键的DSP问题是设计一个数据驱动模型来预测用户转换。为了处理这项艰巨的任务,我们提出了一种新颖的多目标优化(MO)方法,该方法使用语法演化(GE)来演化决策树(DT),主要有以下两种变体:纯GE方法(MGEDT)和带有Lamarckian的GE进化(MGEDTL)。两种变体都演化出可变长度DT,并同时优化预测性能和模型复杂性。为了处理大数据,GE方法包括训练采样和并行度评估机制。将该算法应用于最近的数据库中,该数据库具有来自现实世界DSP的大约600万条记录。使用逼真的滚动窗口(RW)验证,将这两个GE变体与标准DT算法(CART),随机森林和最新的深度学习(DL)模型进行了比较。通过GE方法获得了具有竞争力的结果,该方法具有可承受的培训时间和非常快的预测响应时间。

更新日期:2020-11-21
down
wechat
bug