This paper presents two recommendation models, one traditional and one novel, for a retail men's clothing company. J. Hilburn is a custom-fit, menswear clothing company headquartered in Dallas, Texas. J. Hilburn employs stylists across the United States, who engage directly with customers to assist in selecting clothes that fit their size and style. J. Hilburn tasked the authors of this paper to leverage data science techniques to the given data set to provide stylists with more insight into clients’ purchase patterns and increase overall sales. This paper presents two recommendation systems which provide stylists with automatic predictions about possible clothing interests of their clients. The first recommendation system is a commonly used content-based collaborative filtering model and serves as the base model to evaluate the second recommendation system. The second recommendation system is an ensemble model comprised of separate clustering, KNN, and time series models that is a novel approach. These models are then fed into a neural network in order to produce recommendations. These recommendations for J. Hilburn’s clients will hopefully lead to expanding their customer base and increasing their revenue as a result of more refined clothing and style recommendations. This paper describes the process of building two recommendation systems. Both models are evaluated using AUC as a metric as well as their potential for scalability. The ensemble model has a slightly higher AUC, 91\% versus 86\%. However, the ensemble model is computationally more extensive resulting in it requiring more resources to run.
Leininger, Lisa; Gipson, Johnny; Patterson, Kito; and Blanchard, Brad
"Advancing Performance of Retail Recommendation Systems,"
SMU Data Science Review: Vol. 3:
1, Article 6.
Available at: https://scholar.smu.edu/datasciencereview/vol3/iss1/6
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License