STUDY OF THE INFLUENCE OF CHANGING THE PARAMETERS OF THE ARIMA MODEL ON THE QUALITY OF THE FORECAST FOR SHORT DATA SETS
DOI:
https://doi.org/10.14529/ctcr210304Keywords:
ARIMA, econometrics, analysis, time seriesAbstract
Time series, i.e. data collected at various times. The data collection segments may differ depending on the task. Time series are used for decision making. Time series analysis allows you to get some result that will determine the format of the decision. Time series analysis was carried out in very ancient times, for example, various calendars became a consequence of the analysis. Later, time series analysis was applied to study and forecast economic, social and other systems. Time series appeared a long time ago. Once upon a time, ancient Babylonian astronomers, studying the positionof the stars, discovered the frequency of eclipses, which allowed them to predict their appearance in the future. Later, the analysis of time series, in a similar way, led to the creation of various calendars, for example, harvest calendars. In the future, in addition to natural areas, social and economic ones were added. Aim. Search for classification patterns of time series, allowing to understand whether
it is possible to apply the ARIMA model for their short-term (3 counts) forecast. Materials and methods. Special software with ARIMA implementation and all need services is made. We examined 59 data sets with a short length and step equal a year, less than 20 values in the paper. The data was processed using Python libraries: Statsmodels and Pandas. The Dickey – Fuller test was used to determine the stationarity of the series. The stationarity of the time series allows for better forecasting. The Akaike information criterion was used to select the best model. Recommendations for a reasonable selection of parameters for adjusting ARIMA models are obtained. The dependence of the settings on the category of annual data set is shown. Conclusion. After processing the data, four categories (patterns) of year data sets were identified. Depending on the category ranges of parameters were selected for tuning ARIMA models. The suggested ranges will allow to determine the starting parameters for exploring similar datasets. Recommendations for improving the quality of post-forecast and forecast using the ARIMA model by adjusting the settings are given.
References
Бокс, Дж. Анализ временных рядов, прогноз и управление / Дж. Бокс, Г. Дженкинс; пер. с англ. под ред. В.Ф. Писаренко. – М.: Мир, 1974. – Кн. 1. – 406 с.
Семенов, А.В. Анализ временных рядов в политической науке: возможности и ограничения / А.В. Семенов // Политическая наука. – 2021. – № 1. – С. 76–97.
Khan, F.M. ARIMA and NAR based prediction model for time series analysis of COVID-19 cases in India / F.M. Khan, R. Gupta // Journal of Safety Science and Resilience. – 2020. – Vol. 1, iss. 1. –
P. 12–18. DOI: 10.1016/j.jnlssr.2020.06.007
Abonazel, M.R. Forecasting Egyptian GDP Using ARIMA Models / M.R. Abonazel, A.I. Abd-Elftah // Reports on Economics and Finance. – 2019. – Vol. 5, no. 1. – P. 35–47. DOI: 10.12988/ref.2019.81023
Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks / M.J. Kane, N. Price, M. Scotch et al. // BMC Bioinformatics 15. – 2014. – Vol. 276. DOI: 10.1186/1471-2105-15-276
Верзунов, С.Н. Краткосрочное прогнозирование индекса качества воздуха на основе ARIMA‐моделей / С.Н. Верзунов, Н.М. Лыченко // Сборник материалов VII Международной научной конференции, посвященной памяти С.С. Ефимова. – Омск, 2020. – C. 76–78.
Раднаев, Б.Б. ARIMA-модель пульсового сигнала / Б.Б. Раднаев, А.С. Цыбиков, Б.В. Хабитуев // Вестник БГУ. Математика, информатика. – 2017. – № 1. – С. 78–85.
Янченко, Т.В. Метод управления развитием социального ресурса региона на основе регрессионно-дифференциального моделирования / Т.В. Янченко, А.В. Затонский // Управление большими системами: сб. тр. – 2015. – № 54. – С. 86–113.
Затонский, А.В. Преимущества дифференциальной модели сложной экономической системы / А.В. Затонский, Н.А. Сиротина // Образование. Наука. Научные кадры. – 2012. – № 8. – С. 98–102.
Дуброва, Т.А. Статистические методы прогнозирования: учеб. пособие для вузов /
Т.А. Дуброва. – М.: ЮНИТИ-ДАНА, 2003. – 206 с.
Wang, W. Autoregressive Model-Based Gear Fault Diagnosis / W. Wang, A.K. Wong // Journal of Vibration and Acoustics. – 2002. – Vol. 124 (2). – P. 172–179. DOI: 10.1115/1.1456905
Gupta, R. The impact of US uncertainty on the Euro area in good and bad times: evidence from a quantile structural vector autoregressive model / R. Gupta, C.K.M. Lau, M.E. Wohar // Empirica. – 2018. – Vol. 46. – P. 353–368. DOI: 10.1007/s10663-018-9400-3
Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction / M. Mehedi Hassan, Sh. Huda, J. Yearwood et al. // Information Fusion. – 2018. – Vol. 41. – P. 105–118. DOI: 10.1016/j.inffus.2017.08.004
Optimized Dickey-Fuller Test Refines Sign and Boundary Problems Compare to Traditional Dickey-Fuller Test / I. Masudul, A. Afroza, M. Sirajum et al. // International Journal of Statistics and Probability. – 2018. – Vol. 7, no. 5. – P. 19–27. DOI: 10.5539/ijsp.v7n5p19
Forecasting E-Commerce Products Prices by Combining an Autoregressive Integrated Moving Average (ARIMA) Model and Google Trends Data / S. Carta, A. Medda, A. Pili et al. // Future Internet. – 2019. – Vol. 11 (1), 5. DOI: 10.3390/fi11010005
Akaike, H. A new look at the statistical model identification / H. Akaike // IEEE Transactions on Automatic Control. – 1974. – Vol. 19. – P. 716–723.
Akaike's Information Criterion, Cp and estimators of loss for elliptically symmetric distributions / A. Boisbunon, S. Canu, D. Fourdrinier et al. // International Statistical Review. – 2014. – Vol. 82 (3). – P. 422–439. DOI: 10.1111/insr.12052
