Comparative Analysis of Classification Algorithms for Predicting Membership Churn in Fitness Centers: Case Study and Predictive Modeling at EightGym Indonesia

Authors

  • Dewi Lestari Mu'ti Mercu Buana University of Yogyakarta, Indonesia
  • Putri Taqwa Prasetyaningrum Mercu Buana University of Yogyakarta, Indonesia
Pages Icon

DOI:

https://doi.org/10.51519/journalisi.v7i2.1120

Keywords:

Gym churn prediction, fitness industry, Random Forest vs SVM vs XGBoost, customer retention, machine learning for gyms

Abstract

The fitness industry in Yogyakarta is experiencing rapid growth accompanied by intense competition among gym service providers. This has led to an increase in membership churn, negatively impacting business sustainability. This study aims to conduct a comparative analysis of three supervised classification algorithms Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) to predict member churn at EightGym Indonesia. The dataset, consisting of 1,287 membership records collected between July 2024 and April 2025, includes features such as visit frequency, subscription duration, membership type, and churn status. The study focuses on predicting members at risk of subscription cancellation using historical data such as visit frequency, subscription duration, membership type, and churn status. The methodology follows the CRISP-DM framework, covering business understanding, data preparation, modeling, evaluation, and deployment stages. Evaluation results indicate that XGBoost delivers the best performance with 95% accuracy, high recall, and F1-score, making it the most effective algorithm for churn prediction in this context. Additionally, the model was implemented in a web-based prototype application to support gym management decision-making. The findings contribute significantly to the application of machine learning for customer retention strategies in the fitness industry and provide a foundation for the future development of predictive decision support systems.

Downloads

Download data is not yet available.

References

R. L. Siegel, T. B. Kratzer, A. N. Giaquinto, H. Sung, and A. Jemal, “Cancer statistics, 2025.,” CA. Cancer J. Clin., no. October 2024, pp. 10–45, 2025, doi: 10.3322/caac.21871.

H. M. Bizuayehu et al., “Global Disparities of Cancer and Its Projected Burden in 2050.,” JAMA Netw. open, vol. 7, no. 11, p. e2443198, 2024, doi: 10.1001/jamanetworkopen.2024.43198.

K. Kesehatan and R. Indonesia, “Rencana kanker nasional 2024-2034,” no. September, 2024.

V. Davalos and M. Esteller, “Cancer epigenetics in clinical practice,” CA. Cancer J. Clin., vol. 73, no. 4, pp. 376–424, 2023, doi: 10.3322/caac.21765.

N. Khan, F. Afaq, and H. Mukhtar, “Lifestyle as risk factor for cancer: Evidence from human studies,” Cancer Lett., vol. 293, no. 2, pp. 133–143, 2010, doi: 10.1016/j.canlet.2009.12.013.

P. Marino et al., “Healthy Lifestyle and Cancer Risk: Modifiable Risk Factors to Prevent Cancer,” Nutrients, vol. 16, no. 6, pp. 1–28, 2024, doi: 10.3390/nu16060800.

E. Weiderpass, “Lifestyle and cancer risk,” J. Prev. Med. Public Heal., vol. 43, no. 6, pp. 459–471, 2010, doi: 10.3961/jpmph.2010.43.6.459.

R. Sharman, Z. Harris, B. Ernst, D. Mussallem, A. Larsen, and K. Gowin, “Lifestyle Factors and Cancer: A Narrative Review,” Mayo Clin. Proc. Innov. Qual. Outcomes, vol. 8, no. 2, pp. 166–183, 2024, doi: 10.1016/j.mayocpiqo.2024.01.004.

T. J. Gumilang and B. Hernawan, “The Benefits of Physical Activity to Reduce Mortality in Postmenopausal Breast Cancer Patients: A Literature Review,” Indones. J. Cancer, vol. 17, no. 1, p. 73, 2023, doi: 10.33371/ijoc.v17i1.917.

J. Semrl and A. Matei, “Churn prediction model for effective gym customer retention,” in Proc. 2017 Int. Conf. Behavioral, Economic, Socio-cultural Computing (BESC), 2017, pp. 1–3.

C. Yeomans, A. Karg, and J. Nguyen, “Who churns from fitness centres? Evidence from behavioural and attitudinal segmentation,” Manag. Sport Leis., vol. 0472, pp. 1–17, 2024, doi: 10.1080/23750472.2024.2305896.

M. M. S. Nurhidayat and Dyah Anggraini, “Analysis and Classification of Customer Churn Using Machine Learning Models,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 6, pp. 1253–1259, 2023, doi: 10.29207/resti.v7i6.4933.

M. Imani, A. Beikmohammadi, and H. R. Arabnia, “Comprehensive Analysis of Random Forest and XGBoost Performance with SMOTE, ADASYN, and GNUS Under Varying Imbalance Levels,” Technologies, vol. 13, no. 3, pp. 0–39, 2025, doi: 10.3390/technologies13030088.

R. Krishna, D. Jayanthi, D. S. Shylu Sam, K. Kavitha, N. K. Maurya, and T. Benil, “Application of machine learning techniques for churn prediction in the telecom business,” Results Eng., vol. 24, no. August, p. 103165, 2024, doi: 10.1016/j.rineng.2024.103165.

X. Li and Z. Li, “A hybrid prediction model for e-commerce customer churn based on logistic regression and extreme gradient boosting algorithm,” Ing. des Syst. d’Information, vol. 24, no. 5, pp. 525–530, 2019, doi: 10.18280/isi.240510.

J. Maan and H. Maan, “Customer Churn Prediction Model using Explainable Machine Learning,” arXiv, vol. 11, no. 1, pp. 33–38, 2023.

C. Bentéjac, A. Csörgő, and G. Martínez-Muñoz, “A Comparative Analysis of XGBoost,” arXiv, pp. 1–20, 2019, doi: 10.1007/s10462-020-09896-5.

M. R. Khan, J. Manoj, A. Singh, and J. Blumenstock, “Behavioral Modeling for Churn Prediction: Early Indicators and Accurate Predictors of Custom Defection and Loyalty,” Proc. - 2015 IEEE Int. Congr. Big Data, BigData Congr. 2015, pp. 677–680, 2015, doi: 10.1109/BigDataCongress.2015.107.

S. M. Sina Mirabdolbaghi and B. Amiri, “Model Optimization Analysis of Customer Churn Prediction Using Machine Learning Algorithms with Focus on Feature Reductions,” Discret. Dyn. Nat. Soc., vol. 2022, 2022, doi: 10.1155/2022/5134356.

A. Dhini and M. Fauzan, “Predicting Customer Churn using ensemble learning: Case Study of a Fixed Broadband Company,” Int. J. Technol., vol. 12, no. 5, pp. 1030–1037, 2021, doi: 10.14716/ijtech.v12i5.5223.

C.-F. Tsai and Y.-H. Lu, “Customer churn prediction by hybrid neural networks,” Expert Syst. Appl., vol. 36, no. 10, pp. 12547–12553, 2022.

A. U. Haspriyanti and P. W. Prasetyaningrum, “Penerapan Data Mining Untuk Prediksi Layanan Produk Indihome Menggunakan Metode K-Nearst Neighbor Arwa,” Inf. Syst. Artif. Intell., vol. 20, no. 2, pp. 100–107, 2021.

D. Ruswanti, D. Susilo, and R. Riani, “Implementasi CRISP-DM pada Data Mining untuk Melakukan Prediksi Pendapatan dengan Algoritma C.45,” Go Infotech J. Ilm. STMIK AUB, vol. 30, no. 1, pp. 111–121, 2024, doi: 10.36309/goi.v30i1.266.

R. Wirth and J. Hipp, “CRISP-DM: towards a standard process model for data mining. Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining, 29-39,” Proc. Fourth Int. Conf. Pract. Appl. Knowl. Discov. Data Min., no. 24959, pp. 29–39, 2000.

C. Lukita, L. D. Bakti, U. Rusilowati, A. Sutarman, and U. Rahardja, “Predictive and Analytics using Data Mining and Machine Learning for Customer Churn Prediction,” J. Appl. Data Sci., vol. 4, no. 4, pp. 454–465, 2023, doi: 10.47738/jads.v4i4.131.

Downloads

Published

2025-06-30

Issue

Vol. 7 No. 2 (2025): June

Section

Articles

License

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

How to Cite

[1]
D. L. Mu'ti and P. T. Prasetyaningrum, “Comparative Analysis of Classification Algorithms for Predicting Membership Churn in Fitness Centers: Case Study and Predictive Modeling at EightGym Indonesia”, journalisi, vol. 7, no. 2, pp. 1592–1611, Jun. 2025, doi: 10.51519/journalisi.v7i2.1120.

Most read articles by the same author(s)