Improvement of Drift-Diffusion Models: Use of partial information and reflect of psychological effects

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K01986
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 07090:Commerce-related
• Research Institution: Fukuoka Institute of Technology (2021-2022); Gunma University (2020)
• Principal Investigator: Takahashi Kei 福岡工業大学, 情報工学部, 准教授 (70595280)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: 離散選択 / 心理的効果 / マーチャンダイジング

Outline of Final Research Achievements

In this study, we developed the Drift-Diffusion (DDM) model, which is a discrete decision-making model for short periods of time, by extending the model so that it can theoretically reflect psychological effects represented by the similarity effect, and by reflecting partial information about what people are looking at at that moment using eye cameras. We constructed a consumer behavior model with higher accuracy. Specifically, the similarity effect was incorporated into the DDM in a way that corresponds to a model with a Nest structure, such as the Generalized Nested Logit Model, which was previously studied by the representative researcher. The generation of the similarity effect was confirmed in DDM through an experiment in which potato chips with similar packages were selected.

Free Research Field

マーケティング

Academic Significance and Societal Importance of the Research Achievements

本研究で得られた知見は，実店舗における即時プロモーション等 e-commerce に押されがちである実店舗における施策の立案，評価に応用することができる．今回構築したモデルを基礎とし，カメラ等による個人の実店舗内行動や視線を追跡することにより，見ている商品のプロモーションが有効な場合にはそのプロモーションを行うことにより，当該商品の訴求をより効率的かつ自動に行うシステムの構築へ応用可能であると考えられる．