Reference for citation: Sobolevsky V. А. Automating the creation of machine learning models for solving time series forecasting problems. Journal of Instrument Engineering. 2024. Vol. 67, N 11. P. 951–957 (in Russian). DOI: 10.17586/0021-3454- 2024-67-11-951-957.

Abstract. It is proposed to use the AutoML approach to automate the creation of machine learning models predicting time series. Algorithms and technologies allowing to implement the automation of model creation are considered. A hybrid architecture of machine learning used in solving problems of automating the structural-parametric synthesis of models and optimizing hyperparameters, as well as in the automatic selection of indicators for assessing the quality of synthesized models, is chosen. The user interface for this system is implemented on the basis of the AutoGenNet platform, which embodies the No-Code development concept, which allows hiding the complexity of the processes of creating and training models from users, which reduces the entry threshold for working with the program. Using the AutoGenNet platform allows implementing a mechanism for generating software shells for operating trained models, as well as automating the processes of generating and training hybrid models, which simplifies and speeds up the process of solving time series forecasting problems using machine learning models. The results obtained can be scaled and used to create time series forecasting models in various applied problems.

Keywords: machine learning, time series forecasting, AutoML, linear regression, XGBoost

Acknowledgement: the research conducted on this topic was carried out with partial financial support from budget topic No. FFZF-2022-0004.

References:

1. Houndekindo F., Ouarda T.B.M.J. Energy, 2024, vol. 299, art. no. 131518.
2. Moreno F.P., Rodriguez F.I., Comendador V.F.G., Jurado R. D.-A., Suarez M.Z., Valdes R.M.A. Journal of Air Transport Management, 2024, vol. 119, art. no. 102632.
3. Cooper C., Zhang J., Ragai I., Gao R.X. Journal of Manufacturing Systems, 2024, no. 1–4(75), https://doi. org/10.1016/j.jmsy.2024.04.010.
4. Kebede Y.B., Yang M.D., Huang C.-W. Engineering Applications of Artificial Intelligence, 2024, vol. 135, art. no. 08870.
5. Naeini S.S., Snaiki R. Ocean Engineering, 2024, vol. 295, art. no. 116986.
6. Castillo A.F., Garibay M.V., Diaz-Vazquez D., Yebra-Montes C., Brown L.E., Johnson A., Garcia-Gonzalez A., Gradilla- Hernandez M.S. Ecological Informatics, 2024, vol. 82, art. no. 102655.
7. Feurer M., Klein A., Eggensperger K., Springenberg T.J., Blum M., Hutter F. Automated Machine Learning, 2019, рр. 113–134, DOI:10.1007/978-3-030-05318-5_6.
8. Jin H., Song Q., Hu X. Proc. of the 25th ACM SIGKDD Intern. Conf. on Knowledge Discovery & Data Mining — KDD’19, 2019, DOI:10.1145/3292500.3330648.
9. Shure L. Building Optimized Models in a few steps with AutoML, 2020, https://blogs.mathworks.com/loren/2020/06/13/ building-optimized-models-in-a-few-steps-with-automl/.
10. Zeng Y., Zhang J. Computers in Biology and Medicine, 2020, vol. 122, art. no. 103861.
11. Chen T., Guestrin C. 22nd ACM SIGKDD International Conference, August 2016, DOI:10.1145/2939672.2939785.
12. McCall J. Journal of Computational and Applied Mathematics, 2005, no. 1(184), pp. 205–222.
13. Sobolevskii V.A. CEUR Workshop Proceedings, 2020, vol. 2803, рр. 100–106.
14. Mikhailov V.V., Ponomarenko M.R., Sobolevsky V.A. Global'nyye klimaticheskiye izmeneniya: regional'nyye effekty, modeli, prognozy (Global Climate Change: Regional Effects, Models, Forecasts), Proceedings of the Intern. Sci. and Pract. Conf., Voronezh, 2019, vol. 2, рр. 106–109. (in Russ.)
15. Certificate on the state registration of the computer programs 2021668925, Programma avtomatizirovannoy generatsii i obucheniya iskusstvennykh neyronnykh setey (Program for Automated Generation and Training of Artificial Neural Networks), B.V. Sokolov, V.A. Sobolevsky, Priority 22.10.2021. (in Russ.)
16. Sobolevsky V.A. Informatization and communication, 2024, no. 1, pp. 90–97. (in Russ.)