Revolutionizing Footwear Recommendations: A Data-Driven Approach Harnessing Advanced Machine Learning Techniques

Sing Hoi Leo Zhuang

doi:10.62051/66n15g82

Authors

Sing Hoi Leo Zhuang

DOI:

https://doi.org/10.62051/66n15g82

Keywords:

Footwear Recommendations; Machine Learning; Random Forest; Personalized Fitting; Biomechanical Insights.

Abstract

The footwear landscape is evolving. Individuals seek a personalized shoe and insole fit for enhanced comfort and health. Historically, footwear sizes were measured manually. This traditional method faced challenges in scalability and precision. The study leveraged big data and machine learning to refine shoe size recommendations. Data was sourced from online platforms, foot scanning devices, and user feedback. Rigorous preprocessing ensured the data's consistency and normalization. Multiple machine learning models were evaluated, with the Random Forest algorithm emerging as the most effective. The findings highlighted an improvement in recommendation accuracy.The research indicates that the integration of technology and data holds the potential to transform the footwear industry, prioritizing comfort and health.

Downloads

Download data is not yet available.

References

Moore S R, Kranzinger C, Fritz J, et al. Foot strike angle prediction and pattern classification using LoadsolTM wearable sensors: a comparison of machine learning techniques[J]. Sensors, 2020, 20(23): 6737.

Alcacer A, Epifanio I, Valero J, et al. Combining classification and user-based collaborative filtering for matching footwear size[J]. Mathematics, 2021, 9(7): 771.

Smyth B, Lawlor A, Berndsen J, et al. Recommendations for marathon runners: on the application of recommender systems and machine learning to support recreational marathon runners[J]. User Modeling and User-Adapted Interaction, 2022, 32(5): 787-838.

Salzano M Q, Weir G, Thompson J, et al. Can footwear satisfaction be predicted from mechanical properties?[J]. Footwear Science, 2022, 14(3): 151-161.

Speiser J L, Miller M E, Tooze J, et al. A comparison of random forest variable selection methods for classification prediction modeling[J]. Expert systems with applications, 2019, 134: 93-101.

Schonlau M, Zou R Y. The random forest algorithm for statistical learning[J]. The Stata Journal, 2020, 20(1): 3-29.

Sekulić, A., Kilibarda, M., Heuvelink, G. B., Nikolić, M., & Bajat, B. (2020). Random forest spatial interpolation. Remote Sensing, 12(10), 1687.

Oliveira J, Gomes R, Gonzalez D, et al. Footwear segmentation and recommendation supported by deep learning: an exploratory proposal[J]. Procedia Computer Science, 2023, 219: 724-735.

Horst, F., Hoitz, F., Slijepcevic, D., Schons, N., Beckmann, H., Nigg, B. M., & Schöllhorn, W. I. (2023). Identification of subject-specific responses to footwear during running. Scientific Reports, 13(1), 11284.