Use of constructive-production modeling methods for forecasting deterministic time series
DOI:
https://doi.org/10.34185/1562-9945-5-161-2025-12Keywords:
software, information technologies, constructive-production modeling, fractals, fractal time series, genetic algorithm, L-systemAbstract
Time series forecasting is one of the key tasks of modern data analysis and complex sys-tems modeling. This paper considers the application of a constructive-production approach to deterministic fractal time series. The aim of the study is to reconstruct a constructive model that reflects the internal structure of the series and allows its continuation according to defined generation rules. To verify the effectiveness of the approach, a set of synthetic series generated by constructive models of varying levels of complexity was formed. In turn, the reconstruction of the models was carried out using a specialized software application. The forecasting capability of the method was tested by comparative analysis with classical forecasting models, in particular ARIMA, LSTM, ARIMA-LSTM, and CNN-LSTM. Accuracy was evaluated using MAE and MAPE metrics. The results showed that constructive-production modeling provides the highest forecasting accuracy among all tested models, which is expected given the nature of the input series. It is important to emphasize that, unlike traditional methods, this approach makes it possible to obtain not only forecast values, but also a constructive model of the time series, which can be used for further structural analysis, identification of patterns, and study of properties. Thus, the study confirms the efficiency and feasibility of using constructive-production modeling for forecasting deterministic fractal time series.
References
Weigend A. Time Series Prediction: Forecasting the Future and Understanding the Past. London, 2018. URL: https://doi.org/10.4324/9780429492648.
Park M.-J., Yang H.-S. Comparative Study of Time Series Analysis Algorithms Suitable for Short-Term Forecasting in Implementing Demand Response Based on AMI. Sensors. 2024. Vol. 24, No. 22. P. 7205. URL: https://doi.org/10.3390/s24227205.
Shu Z., Chan P.W. Application of fractal analysis on wind speed time series: A review. Advances in Wind Engineering, 2025, vol. 2, no. 1, p. 100028. ISSN 2950-6018. URL: https://doi.org/10.1016/j.awe.2024.100028.
Skalozub V., Ilman V., Bilyy B. Constructive multiplayer models for ordering a set of sequences, taking into account the complexity operations of formations. Science and Transport Progress. Bulletin of Dnipropetrovsk National University of Railway Transport, 2020, pp. 61–76. URL: https://doi.org/10.15802/stp2020/213232.
Shynkarenko K., Lytvynenko R., Chyhir I., Nikitina I. Modeling of lightning flashes in thunderstorm front by constructive production of fractal time series. In: Advances in Intelligent Systems and Computing, vol. 1080, Springer, 2020, pp. 173–185.
URL: https://doi.org/10.1007/978-3-030-33695-0_13.
Foroutan P., Lahmiri S. Deep learning systems for forecasting the prices of crude oil and precious metals. Financial Innovation, 2024, vol. 10, p. 111.
URL: https://doi.org/10.1186/s40854-024-00637-z.
Khan A.M., Osinska M. Comparing forecasting accuracy of selected grey and time series models based on energy consumption in Brazil and India. Expert Systems with Applications, 2023, vol. 212, p. 118840. ISSN 0957-4174.
URL: https://doi.org/10.1016/j.eswa.2022.118840.
Shynkarenko V., Zhadan A. Modeling of the deterministic fractal time series by one rule constructors. 2020 IEEE 15th International Conference on Computer Sciences and Information Technologies (CSIT), Zbarazh, Ukraine, 2020, pp. 336–339.
URL: https://doi.org/10.1109/CSIT49958.2020.9321923.
Serletis A., Rosenberg A.A. The Hurst exponent in energy futures prices. Physica A: Statistical Mechanics and its Applications, 2007, vol. 380, pp. 325–332.
Prusinkiewicz P., Lindenmayer A. The algorithmic beauty of plants. Springer Science & Business Media, 2012.
Tsukamoto M. Mean Hausdorff dimension of some infinite-dimensional fractals. Journal d’Analyse Mathématique, 2025, vol. 155, pp. 235–286. URL: https://doi.org/10.1007/s11854-024-0353-0.
Ospina R., Gondim J.A.M., Leiva V., Castro C. An overview of forecast analysis with ARIMA models during the COVID-19 pandemic: Methodology and case study in Brazil. Mathematics, 2023, vol. 11, p. 3069. URL: https://doi.org/10.3390/math11143069.
Tarmanini C., Sarma N., Gezegin C., Ozgonenel O. Short term load forecasting based on ARIMA and ANN approaches. Energy Reports, 2023, vol. 9, suppl. 3, pp. 550–557. ISSN 2352-4847. URL: https://doi.org/10.1016/j.egyr.2023.01.060.
Bhalla V., Bhalla A., Jain R. A comparison of ARIMA, SARIMA, and statistical models for estimating. In: Sustainable Computing and Intelligent Systems: Proceedings of SCIS 2024, vol. 2, 1296, 2025, p. 185.
Ray S., Lama A., Mishra P., Biswas T., Das S.S., Gurung B. An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique. Applied Soft Computing, 2023, vol. 149, part A, p. 110939. ISSN 1568-4946.
URL: https://doi.org/10.1016/j.asoc.2023.110939.
Salem F.M. Recurrent Neural Networks (RNN). In: Recurrent Neural Networks. Cham: Springer, 2022. URL: https://doi.org/10.1007/978-3-030-89929-5_3.
Al-Selwi S.M., Hassan M.F., Abdulkadir S.J., Muneer A., Sumiea E.H., Alqushaibi A., Ragab M.G. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University - Computer and Information Sciences, 2024, vol. 36, no. 5, p. 102068. ISSN 1319-1578.
URL: https://doi.org/10.1016/j.jksuci.2024.102068.
Md A.Q., Kapoor S., Junni A.V.C., Sivaraman A.K., Tee K.F., Sabireen H., Janakiraman N. Novel optimization approach for stock price forecasting using multi-layered sequential LSTM. Applied Soft Computing, 2023, vol. 134, p. 109830. ISSN 1568-4946.
URL: https://doi.org/10.1016/j.asoc.2022.109830.
Wang K., Zhang J., Li X., Zhang Y. Long-term power load forecasting using LSTM-Informer with ensemble learning. Electronics, 2023, vol. 12, p. 2175.
URL: https://doi.org/10.3390/electronics12102175.
Elmaz F., Eyckerman R., Casteels W., Latré S., Hellinckx P. CNN-LSTM architecture for predictive indoor temperature modeling. Building and Environment, 2021, vol. 206, p. 108327. ISSN 0360-1323. URL: https://doi.org/10.1016/j.buildenv.2021.108327.
Wu J.M.T., Li Z., Herencsar N., et al. A graph-based CNN-LSTM stock price prediction algorithm with leading indicators. Multimedia Systems, 2023, vol. 29, pp. 1751–1770.
URL: https://doi.org/10.1007/s00530-021-00758-w
Wang J.-D., Susanto C.O.N. Traffic flow prediction with heterogenous data using a hybrid CNN-LSTM model. Computers, Materials and Continua, 2023, vol. 76, no. 3, pp. 3097–3112. ISSN 1546-2218. URL: https://doi.org/10.32604/cmc.2023.040914.
Zha W., Liu Y., Wan Y., Luo R., Li D., Yang S., Xu Y. Forecasting monthly gas field production based on the CNN-LSTM model. Energy, 2022, vol. 260, p. 124889. ISSN 0360-5442. URL: https://doi.org/10.1016/j.energy.2022.124889.
Ray S., Lama A., Mishra P., Biswas T., Das S.S., Gurung B. An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique. Applied Soft Computing, 2023, vol. 149, part A, p. 110939. ISSN 1568-4946.
URL: https://doi.org/10.1016/j.asoc.2023.110939.
Jin Y.-C., Cao Q., Wang K.-N., Zhou Y., Cao Y.-P., Wang X.-Y. Prediction of COVID-19 data using improved ARIMA-LSTM hybrid forecast models. IEEE Access, 2023, vol. 11, pp. 67956–67967. URL: https://doi.org/10.1109/ACCESS.2023.3291999.
Shynkarenko V., Zhadan A. Multiservice architecture of software for stochastic fractal time series forecasting. 2024 IEEE Conference on Computer Sciences and Information Technologies, 2024, pp. 1–4. URL: https://doi.org/10.1109/CSIT65290.2024.10982626.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
