Flexible Purchase Frequency Modeling
提出一个灵活的购买频率建模框架，能拟合多种分布并简化计算，用第一期的购买频率预测第二期，适用于四个营销面板数据集。
The authors present a general framework for purchase frequency modeling that enables flexible fitting and convenient computation. Their easily described purchase frequency distributions subsume many previous models and provide a connection between mixed Poisson marketing models and the conceptually distinct compound Poisson models. These distributions provide simple parametric equations for individual-level prediction of second-period purchase frequency based on observed first-period purchase frequencies. The results are applied to four marketing panel data sets.