Competition-Aware CPC Forecasting with Near-Market Coverage
竞争感知的CPC预测与近市场覆盖
机构 * Nova School of Business and Economics(新里斯本大学商业与经济学院) ; University of Hamburg(汉堡大学)
专题命中 规划推理 :planning(abstract);分类 cs.AI、cs.LG
AI总结 针对付费搜索中部分可观测的竞争环境,提出结合语义邻域、行为邻域和地理意向协变量的竞争感知CPC预测方法,在短期(1周)图模型降低sMAPE 15.1%,长期(6-12周)协变量增强基础模型降低sMAPE 22.5%-27.6%。
Comments 17 pages, 2 figures, 6 tables, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), the code is availale at https://github.com/Sebastian-Frey/Competition-Aware-GNNs-for-TimeSeriesForecasting