IJBTT

Personalized Gym Recommendation System Using Machine Learning

Personalized Gym Recommendation System Using Machine Learning
	© 2025 by IJETT Journal
	Volume-73 Issue-4
	Year of Publication : 2025
	Author : Abdifatah Ahmed Gedi, Abdullahi Ali Khalif, Mascud Abdirahman Sheikh Doon, Ayan Abdullahi Mohamed, Iqra Abdi Ali, Bashir Abdinur Ahmed
	DOI : 10.14445/22315381/IJETT-V73I4P122

How to Cite?
Abdifatah Ahmed Gedi, Abdullahi Ali Khalif, Mascud Abdirahman Sheikh Doon, Ayan Abdullahi Mohamed, Iqra Abdi Ali, Bashir Abdinur Ahmed, "Personalized Gym Recommendation System Using Machine Learning," International Journal of Engineering Trends and Technology, vol. 73, no. 4, pp.249-257, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I4P122

Abstract
The Personalized Gym Recommendation System (PGRS) is a digital platform designed to provide tailored fitness and health advice to gym-goers, particularly beginners and intermediates. This study introduces an innovative approach to simplify workout routines by leveraging machine learning algorithms to analyze user data and generate personalized recommendations. The dataset, obtained from Kaggle, originally contained 14589 records with 15 columns, and three additional columns were added, resulting in 18 columns. Eight machine learning models were trained for both classification and regression. The Decision Tree regression model worked wonders; the accuracy was 100% against the training set and 99.95% against the test set. Next in line were the results of the Decision Tree classification model, which turned out very good; training accuracy equaled 99.33%, while test accuracy equaled 92.22%. The main challenge in our study was joining regression and classifier classes into a single model. The main difference between these two classes is that regression predicts continuous values, whereas classification does the opposite by grouping data into specific categories.

Keywords
Blockchain technology, Civic engagement, Decentralized systems, Online petitions, Policy-making.

References
[1] Bo Zhou et al., “Measuring Muscle Activities During Gym Exercises with Textile Pressure Mapping Sensors,” Pervasive and Mobile Computing, vol. 38, pp. 331-345, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] J. Jeyaranjani and Utkash Kapoor, “Machine Learning Based Fitness Application Using BMI Value,” Journal of Physics: Conference Series, International Conference on Recent Trends in Computing 20-22, Maharashtra, India, vol. 1979, no. 1, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Anganabha Baruah et al., “Machine Learning Based Yoga Recommendation System for the Physical Fitness,” 8th International Conference on Science Technology Engineering and Mathematics, Chennai, India, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Vaishali S. Vairale, and Samiksha Shukla, “Physical Fitness Recommender Framework for Thyroid Patients using Restricted Boltzmann Machines,” International Journal of Intelligent Engineering & Systems, vol. 13, no. 5, pp. 247-256, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Megh Shah, Sheshang Degadwala, and Dhairya Vyas, “Diet Recommendation System based on Different Machine Learners: A Review,” 2nd International Conference on Artificial Intelligence and Smart Energy, Coimbatore, India, pp. 290-295, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Celestine Iwendi et al., “Realizing an Efficient Iomt-Assisted Patient Diet Recommendation System Through Machine Learning Model,” IEEE access, vol. 8, pp. 28462-28474, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jennifer Smith Maguire, “The Culture of Fitness: Opportunities and Challenges for Health,” Marketing Sport and Physical Activity: Impacts on Health and Leisure: International Sports Marketing Conference, Hong Kong Baptist University, pp. 1-11, 2006.
[Google Scholar] [Publisher Link]
[8] Jesper Andreasson, and Thomas Johansson, “The Fitness Revolution: Historical Transformations in the Global Gym and Fitness Culture,” Sport Science Review, vol. 23, no. 3-4, pp. 91-112, 2014.
[Google Scholar] [Publisher Link]
[9] Paweł W. Woźniak et al., “Exploring Understandable Algorithms to Suggest Fitness Tracker Goals That Foster Commitment,” Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society, Tallinn, Estonia, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Milad Asgari Mehrabadi et al., “PERFECT: Personalized Exercise Recommendation Framework and architECTure,” ACM Transactions on Computing for Healthcare, vol. 5, no. 4, pp. 1-25, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Jianmo Ni, Larry Muhlstein, and Julian McAuley, “Modeling Heart Rate and Activity Data for Personalized Fitness Recommendation,” The World Wide Web Conference, San Francisco, USA, pp. 1343-1353, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Satvik Garg, “Drug Recommendation System Based on Sentiment Analysis of Drug Reviews Using Machine Learning,” 11th International Conference on Cloud Computing, Data Science & Engineering, Noida, India, pp. 175-181, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Xueli Xing, and Qiushi Wen, “A Human Resource Evaluation and Recommendation System based on Big Data Mining,” Scalable Computing: Practice and Experience, vol. 25, no. 6, pp. 5539-5549, 2024.
[CrossRef] [Google Scholar] [Publisher Link]