Improving Purchase Behavior Prediction with Most Popular Items

Chen CHEN; Jiakun XIAO; Chunyan HOU; Xiaojie YUAN

doi:10.1587/transinf.2016EDL8169

Improving Purchase Behavior Prediction with Most Popular Items

Chen CHEN, Jiakun XIAO, Chunyan HOU, Xiaojie YUAN

Full Text Views

0

Cite this

Summary :

Purchase behavior prediction is one of the most important issues to promote both e-commerce companies' sales and the consumers' satisfaction. The prediction usually uses features based on the statistics of items. This kind of features can lead to the loss of detailed information of items. While all items are included, a large number of features has the negative impact on the efficiency of learning the predictive model. In this study, we propose to use the most popular items for improving the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. We also analyze the reason for the performance of the most popular items. In addition, our work also reveals if interactions among most popular items are taken into account, the further significant improvement can be achieved. One possible explanation is that online retailers usually use a variety of sales promotion methods and the interactions can help to predict the purchase behavior.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.2 pp.367-370

Publication Date: 2017/02/01

Publicized: 2016/11/07

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8169

Type of Manuscript: LETTER

Category: Data Engineering, Web Information Systems

Authors

Chen CHEN
  Nankai University
Jiakun XIAO
  Nankai University
Chunyan HOU
  Tianjin University of Technology
Xiaojie YUAN
  Nankai University

Keyword

recommender system, behavior analysis, prediction, e-commerce, session

Cite this

Copy

Chen CHEN, Jiakun XIAO, Chunyan HOU, Xiaojie YUAN, "Improving Purchase Behavior Prediction with Most Popular Items" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 2, pp. 367-370, February 2017, doi: 10.1587/transinf.2016EDL8169.
Abstract: Purchase behavior prediction is one of the most important issues to promote both e-commerce companies' sales and the consumers' satisfaction. The prediction usually uses features based on the statistics of items. This kind of features can lead to the loss of detailed information of items. While all items are included, a large number of features has the negative impact on the efficiency of learning the predictive model. In this study, we propose to use the most popular items for improving the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. We also analyze the reason for the performance of the most popular items. In addition, our work also reveals if interactions among most popular items are taken into account, the further significant improvement can be achieved. One possible explanation is that online retailers usually use a variety of sales promotion methods and the interactions can help to predict the purchase behavior.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8169/_p

Copy

@ARTICLE{e100-d_2_367,
author={Chen CHEN, Jiakun XIAO, Chunyan HOU, Xiaojie YUAN, },
journal={IEICE TRANSACTIONS on Information},
title={Improving Purchase Behavior Prediction with Most Popular Items},
year={2017},
volume={E100-D},
number={2},
pages={367-370},
abstract={Purchase behavior prediction is one of the most important issues to promote both e-commerce companies' sales and the consumers' satisfaction. The prediction usually uses features based on the statistics of items. This kind of features can lead to the loss of detailed information of items. While all items are included, a large number of features has the negative impact on the efficiency of learning the predictive model. In this study, we propose to use the most popular items for improving the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. We also analyze the reason for the performance of the most popular items. In addition, our work also reveals if interactions among most popular items are taken into account, the further significant improvement can be achieved. One possible explanation is that online retailers usually use a variety of sales promotion methods and the interactions can help to predict the purchase behavior.},
keywords={},
doi={10.1587/transinf.2016EDL8169},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Improving Purchase Behavior Prediction with Most Popular Items
T2 - IEICE TRANSACTIONS on Information
SP - 367
EP - 370
AU - Chen CHEN
AU - Jiakun XIAO
AU - Chunyan HOU
AU - Xiaojie YUAN
PY - 2017
DO - 10.1587/transinf.2016EDL8169
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2017
AB - Purchase behavior prediction is one of the most important issues to promote both e-commerce companies' sales and the consumers' satisfaction. The prediction usually uses features based on the statistics of items. This kind of features can lead to the loss of detailed information of items. While all items are included, a large number of features has the negative impact on the efficiency of learning the predictive model. In this study, we propose to use the most popular items for improving the prediction. Experiments on the real-world dataset have demonstrated the effectiveness and the efficiency of our proposed method. We also analyze the reason for the performance of the most popular items. In addition, our work also reveals if interactions among most popular items are taken into account, the further significant improvement can be achieved. One possible explanation is that online retailers usually use a variety of sales promotion methods and the interactions can help to predict the purchase behavior.
ER -