Dynamic Modeling of Consumer Purchase Behavior: Based on Web Crawling Data

2016 Fiscal Year Final Research Report

• Project/Area Number: 15H06747
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Commerce
• Research Institution: Toyo University (2016); Kansai University (2015)
• Principal Investigator: Li Zhen 東洋大学, 経営学部, 講師 (30759923)
• Research Collaborator: ZHANG Jie The University of Maryland, Robert H. Smith School of Business, Professor ; MA Yan 神戸大学, 経営学部, 准教授 ; HUANG Lin 神戸大学, 経営学研究科, 教授 ; YADA Katsutoshi 関西大学, 商学部, 教授
• Project Period (FY): 2015-08-28 – 2017-03-31
• Keywords: 消費者購買行動 / Web Crawling技術 / オンライン市場 / 顧客レビュー / 消費の外部性

Outline of Final Research Achievements

There is much evidence that customer reviews are important to merchants' sales. However, little is deeply discussed about how much the online reviews affect sales, and the validity of the influence also lacks supports of empirical studies. This study posits that sales effects of customer reviews are different by market structure.

We propose a Bayesian statistical model to study how customer reviews affect sales and the difference in its influence between two types of merchants, market-place and self-conducted stores. The data in this study are retrieved by using Web Crawling technology. The findings suggest that (1) sales effects of review volume will be attenuates by the information of sales outcomes in previous period, (2) compared with self-conducted stores, the volume of customer reviews seem more effective on sales for merchants in market-place, and (3) the effects of review valence on sales are also somewhat stronger for market-place stores than it for self-conducted stores.

Free Research Field

マーケティング・サイエンス