Journal of Engineering, Project, and Production Management, 2026, 16(5), 2026-189
Modeling Elderly Dance Interest Preferences and Developing a Dynamic Course Adaptation System Using LightGBM
Ph.D. Candidate, Taizhou University, Taizhou, Jiangsu, 225400, China, E-mail: cuiyalin0222@163.com
Project Management
Received February 4, 2026; revised March 23, 2026; accepted March 23, 2026
Available online June 17, 2026
Abstract: Traditional methods for recommending dance courses for the elderly, due to their static modeling, struggle to adapt to the dynamic changes in senior’s interests, resulting in insufficient course matching accuracy. This paper constructs a Light Gradient Boosting Machine (LightGBM) preference prediction model that leverages temporal feature enhancement and dynamic weight updates and designs a dynamic course adaptation system based on this model. This method extracts statistical and trending features from user behavior sequences through a sliding window to quantify interest drift. The model iteratively fits the residuals of preference labels using a forward distribution algorithm and gradient-boosted decision tree principles, and an exponential decay-based weight update mechanism is applied during the online learning phase to enable the model to continuously track interest evolution. Experimental results show that the model achieves prediction accuracies of 0.328 and 0.426 for the two core indicators, course click-through rate and user satisfaction, respectively. This research provides a highly adaptable and engineering-feasible technical path for optimizing service operations in elderly education, offering a reliable example of adaptive resource allocation and personalized service delivery.
Keywords: Senior dance, interest preference modeling, course recommendation, Light Gradient Boosting Machine (LightGBM) model, dynamic adaptation.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: Cui, Y. (2026). Modeling Elderly Dance Interest Preferences and Developing a Dynamic Course Adaptation System Using LightGBM. Journal of Engineering, Project, and Production Management, 16(5), 2026-189.
