Intelligence Sports Performance Analytics from Strava Using Big Data Platform with Multi-Layer Perceptron

Abstract:

This paper is trying to address the challenge faced by athletes or recreational runners to predict the performance based on historical performance and current condition. Not only based on individual performance, but the sportsman also needs to understand with current health condition, what the peak performance that can achieve. Recent development of big data technology with streaming pipeline is possible to address the challenge. With Strava Application as an edge technology that user used to gather the data and Big Data platform to process the data in stream, this research is trying to address the problem. This paper presents the automatic big data pipeline that retrieve data from multiple smartwatch platform, process the data with machine learning model and visualize the data and result in web visualization. Multi-Layer Perceptron model is providing the best performance with R-square 0.985 and MAPE 0.047 or 4.7%.

• Periodical: Engineering Headway (Volume 27)
• Pages: 364-379
• DOI: https://doi.org/10.4028/p-ZZgA04
• Online since: October 2025
• Authors: Alfian Andi Nugroho*
• Keywords: Big Data Architecture, Data Pipeline, Multi-Layer Perceptron, Multilinear Regression, Strava API

References

[1] W. C. Wei, T. Mizumoto, and K. Yasumoto, "Physical burden prediction for cycling on arbitrary route," Oct. 2018. Accessed: Nov. 21, 2021. [Online]. Available:

DOI: 10.1109/gcce.2018.8574483

[2] H. Huang and E. N. Ceesay, "Statistical and Transfer Learning Model to Analyze Endurance Performance with Aging," 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), 2021, pp.1-6

DOI: 10.1109/IEMTRONICS52119.2021.9422586

[3] M. Altini and O. Amft, "Estimating Running Performance Combining Non-invasive Physiological Measurements and Training Patterns in Free-Living," 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018, pp.2845-2848.

DOI: 10.1109/EMBC.2018.8512924

[4] N. Khasawneh, C. Schulte and M. Fraiwan, "A Framework for Crowd-Sourced Exercise Data Collection and Processing," 2020 11th International Conference on |Information and Communication Systems (ICICS), 2020, pp.313-317.

DOI: 10.1109/ICICS49469.2020.239546

[5] Y. Qiu, X. Zhu and J. Lu, "Fitness Monitoring System Based on Internet of Things and Big Data Analysis," in IEEE Access, vol. 9, pp.8054-8068, 2021.

DOI: 10.1109/ACCESS.2021.3049522

[6] G. Xu et al., "An IoT-Based Framework of Webvr Visualization for Medical Big Data in Connected Health," in IEEE Access, vol. 7, pp.173866-173874, 2019, doi: 10.1109/ACCESS. 2019.2957149

DOI: 10.1109/access.2019.2957149

[7] Stauffer, J., Zhang, Q. s2Cloud: a novel cloud-based precision health system for smart and secure IoT big data harnessing. Discov Internet Things 4, 3 (2024).

DOI: 10.1007/s43926-024-00055-8

[8] "Strava Developers." https://developers.strava.com/ (accessed Nov. 24, 2021).

[9] H. Dagdougui, F. Bagheri, H. Le, and L. Dessaint, "Neural network model for short-term and very-short-term load forecasting in district buildings," Energy and Buildings, vol. 203, p.109408, Nov. 2019.

DOI: 10.1016/j.enbuild.2019.109408

[10] J. Mohammadi, M. Ataei, R. Khalo Kakaei, R. Mikaeil, and S. Shaffiee Haghshenas, "Prediction of the Production Rate of Chain Saw Machine using the Multilayer Perceptron (MLP) Neural Network," Civil Engineering Journal, vol. 4, no. 7, p.1575, Jul. 2018.

DOI: 10.28991/cej-0309196

[11] B. T. Pham, M. D. Nguyen, K.-T. T. Bui, I. Prakash, K. Chapi, and D. T. Bui, "A novel artificial intelligence approach based on Multi-layer Perceptron Neural Network and Biogeography-based Optimization for predicting coefficient of consolidation of soil," CATENA, vol. 173, p.302–311, Feb. 2019.

DOI: 10.1016/j.catena.2018.10.004

[12] F. R. Lima-Junior and L. C. R. Carpinetti, "Predicting supply chain performance based on SCOR® metrics and multilayer perceptron neural networks," International Journal of Production Economics, vol. 212, p.19–38, Jun. 2019

DOI: 10.1016/j.ijpe.2019.02.001

[13] "Python Machine Learning Multiple Regression." https://www.w3schools.com/python/python_ml_multiple_regression.asp (accessed Dec. 05, 2021).

[14] O. El Aissaoui, Y. El Alami El Madani, L. Oughdir, A. Dakkak, and Y. El Allioui, "A Multiple Linear Regression-Based Approach to Predict Student Performance," in Advances in Intelligent Systems and Computing, Cham: Springer International Publishing, 2020, p.9–23. Accessed: Dec. 05, 2021. [Online]. Available:

DOI: 10.1007/978-3-030-36653-7_2

[15] S. Rath, A. Tripathy, and A. R. Tripathy, "Prediction of new active cases of coronavirus disease (COVID-19) pandemic using multiple linear regression model," Diabetes & Metabolic Syndrome: Clinical Research & Reviews, vol. 14, no. 5, p.1467–1474, Sep. 2020.

DOI: 10.1016/j.dsx.2020.07.045

[16] Awad M., Khanna R. (2015) Support Vector Regression. In: Efficient Learning Machines. Apress, Berkeley, CA

DOI: 10.1007/978-1-4302-5990-9_4

[17] B. Panwar, G. Dhuriya, P. Johri, S. Singh Yadav and N. Gaur, "Stock Market Prediction Using Linear Regression and SVM," 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 2021, pp.629-631, doi:10.1109/ ICACITE51222.2021.9404733.

DOI: 10.1109/icacite51222.2021.9404733