TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior

Alves Gomes, Miguel; Wönkhaus, Mark; Meisen, Philipp; Meisen, Tobias

doi:10.3390/jtaer18030070

Open AccessArticle

TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior

¹

Institute for Technologies and Management of Digital Transformation, University of Wuppertal, 42119 Wuppertal, Germany

²

Breinify Inc., San Francisco, CA 94105, USA

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

J. Theor. Appl. Electron. Commer. Res. 2023, 18(3), 1404-1418; https://doi.org/10.3390/jtaer18030070

Submission received: 24 June 2023 / Revised: 10 August 2023 / Accepted: 16 August 2023 / Published: 17 August 2023

(This article belongs to the Topic Online User Behavior in the Context of Big Data)

Download

Browse Figure

Versions Notes

Abstract

Real-time customer purchase prediction tries to predict which products a customer will buy next. Depending on the approach used, this involves using data such as the customer’s past purchases, his or her search queries, the time spent on a product page, the customer’s age and gender, and other demographic information. These predictions are then used to generate personalized recommendations and offers for the customer. A variety of approaches already exist for real-time customer purchase prediction. However, these typically require expertise to create customer representations. Recently, embedding-based approaches have shown that customer representations can be effectively learned. In this regard, however, the current state-of-the-art does not consider activity time. In this work, we propose an extended embedding approach to represent the customer behavior of a session for both known and unknown customers by including the activity time. We train a long short-term memory with our representation. We show with empirical experiments on three different real-world datasets that encoding activity time into the embedding increases the performance of the prediction and outperforms the current approaches used.

Keywords: e-commerce; purchase prediction; real-time purchase prediction; embeddings; time embeddings; customer representation; machine learning

Share and Cite

MDPI and ACS Style

Alves Gomes, M.; Wönkhaus, M.; Meisen, P.; Meisen, T. TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior. J. Theor. Appl. Electron. Commer. Res. 2023, 18, 1404-1418. https://doi.org/10.3390/jtaer18030070

AMA Style

Alves Gomes M, Wönkhaus M, Meisen P, Meisen T. TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior. Journal of Theoretical and Applied Electronic Commerce Research. 2023; 18(3):1404-1418. https://doi.org/10.3390/jtaer18030070

Chicago/Turabian Style

Alves Gomes, Miguel, Mark Wönkhaus, Philipp Meisen, and Tobias Meisen. 2023. "TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior" Journal of Theoretical and Applied Electronic Commerce Research 18, no. 3: 1404-1418. https://doi.org/10.3390/jtaer18030070

APA Style

Alves Gomes, M., Wönkhaus, M., Meisen, P., & Meisen, T. (2023). TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior. Journal of Theoretical and Applied Electronic Commerce Research, 18(3), 1404-1418. https://doi.org/10.3390/jtaer18030070

Article Menu

TEE: Real-Time Purchase Prediction Using Time Extended Embeddings for Representing Customer Behavior

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI