Please use this identifier to cite or link to this item:

Purchase Prediction Based on a Non-parametric Bayesian Method

File Size Format  
0132.pdf 511.92 kB Adobe PDF View/Open

Item Summary

Title:Purchase Prediction Based on a Non-parametric Bayesian Method
Authors:Liu, Yezheng
Zhu, Tingting
Jiang, Yuanchun
Keywords:Decision Support for Smart Cities
Decision Analytics, Mobile Services, and Service Science
purchase prediction,non-parametric bayesian,HDP
Date Issued:08 Jan 2019
Abstract:Predicting customer’s next purchase is of paramount importance for online retailers. In this paper, we present a new purchase prediction method to predict customer behavior based on non-parametric Bayesian framework. The proposed method is inspired by topic modeling for text mining. Unlike the conventional methods, we regard customer’s purchase as the result of motivations and automatically determine the number of user purchase motivations. Given customer’s purchase history, we show that customer’s next purchase can be predicted by non-parametric Bayesian model. We apply the model to real-world dataset from and prove it outperforms the traditional methods. Besides that, the proposed method can also determine the number of the motivations owned by users automatically, rendering it a promising approach with a good scalability.
Pages/Duration:9 pages
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections: Decision Support for Smart Cities

Please email if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons