Time series forecasting is a crucial task in economics, business, and finance. Traditionally, forecasting methods such as autoregression (AR), moving average (MA), exponential smoothing (SES), and, most commonly, the autoregressive integrated moving average (ARIMA) model are used. The ARIMA model has demonstrated high accuracy in predicting future time series values. With the advancement of computational power and deep learning algorithms, new approaches to forecasting have emerged. This paper explores whether deep learning algorithms, such as Long Short-Term Memory (LSTM), are more effective than traditional methods. Empirical studies conducted in this work show that deep learning-based algorithms, such as LSTM, outperform traditional methods like ARIMA. Specifically, the average error reduction when using LSTM is 84-87% compared to ARIMA, indicating the superiority of LSTM.
[1] BOX, G.E.P. and G.M. JENKINS (1970) Time series analysis: Forecasting and control, San Francisco: Holden-Day
[2] Adebiyi A.A., Adewumi A.O., Ayo C.K., 2014. Stock Price Prediction Using the ARIMA Model. UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.
[3] Fischera T., Kraussb C., 2024. Deep Learning with Long Short-term Memory Networks for Financial Market Predictions. FAU Discussion Papers in Economics 11.
[4] Roshchyna N. V, Shevchuk O. A, Kustarova K. M. Doslidzhennia mizhnarodnoho finansovoho rynku v umovakh didzhytalizatsii: novi mozhlyvosti. Ekonomichnyi visnyk NTUU "KPI" № 18. 2021 r. c.45, https://doi.org/10.20535/2307-5651.18.2021.231459
[5] Matveichuk L.O. Tsyfrova ekonomika: teoretychni aspekty. Visnyk Zaporizkoho natsionalnoho universytetu. Seriia: Ekonomichni nauky. 2023. № 4 (40). S. 116—127.
[6] Melnyk T.Iu. Prohnozuvannia sotsialno-ekonomichnykh yavyshch yak instrument obgruntuvannia upravlinskykh rishen. Visnyk ZhDTU. 2018. № 2 (84). S. 90-95
[7] Time Series Analysis and Forecasting. URL: https://www.statgraphics.com/time-series-analysis-andforecasting
[8] Osnovy roboty z systemoiu inzhenernykh ta naukovo-tekhnichnykh obchyslen MATLAB [Elektronnyi resurs]. Rezhym dostupu: https://mte.nure.ua/pdf/studying/zov_itpz_lk6.pdf
[9] Regression in machine learning Popular Regression Algorithms. Jigsaw Academy. URL: https://www.jigsawacademy.com/popular-regressionalgorithms-ml/
[10] Statistical Methods for Forecasting Quantitative Time Series. URL: https://www.bistasolutions.com/resources/blogs/5-statistical-methods-for-forecasting-quantitative-timeseries/#:~:text=Techniques%20of%20Forecasting%3A,Neural%20Network%20(NN)
[11] Teoriia ymovirnostei ta matematychna statystyka: navch. posib. / O. I. Kushlyk, Dyvulska, N. V. Polishchuk, B. P. Orel, P. I. Shtabaliuk. Kyiv: NTUU «KPI», 2014. 212 s.
[12] Koliadenko S. V. Tsyfrova ekonomika: peredumovy ta etapy stanovlennia v Ukraini i u sviti. Ekonomika. Finansy. Menedzhment. 2016. No 6. S. 106–107.