Application of Bayesian Network for Prediction Behavior via Direct Observation of In-store Behavior

2015 Fiscal Year Final Research Report

• Project/Area Number: 25780277
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Commerce
• Research Institution: Nagoya University (2014-2015); Kansai University (2013)
• Principal Investigator: Zuo Yi 名古屋大学, 未来社会創造機構, 助教 (70633684)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: RFIDデータ / 消費者の購買行為 / 消費者の滞在時間 / 退屈現象 / ベイジアンネットワーク

Outline of Final Research Achievements

In strategic management of retail industry, the advanced investigation by using radio frequency identification (RFID) technology to capture customers' in-store behavior has been dramatically attracted scholars and practitioners in recent ages. In contrast to prior studies in this research field, this work has paid special attention to shopping time that customers spent in supermarket (so-called stay time), and presents methodological analysis into two folds. First, due to BN can estimate and predict in a nonlinear correlation between purchase intention and stay time, we examine a tedium effect on purchase behavior. During the customers wander in shopping, purchase intention represents a non-monotonic phenomena accounting for the long stay time. Second, we also investigate the sensitivity and specificity of purchase behavior predicted by our proposal in adjustment of decision threshold and implements several business decision-making implications in actual business situations.

Free Research Field

消費者行動