Updated DTW+K-Means approach with LSTM and ARIMA-type models for Core Inflation forecasting


  • D. Krukovets Taras Shevchenko National University of Kyiv




Dynamic Time Warping, Clustering, ARIMA, Recurrent Neural Networks, LSTM, Forecasting, Inflation


The paper is dedicated to evaluating performance in forecasting tasks of the novel routine that includes adapted DTW + K-Means for aggregating series with similar dynamics. The algorithm was developed throughout the series of papers. Novel parts are designed in a way to work with periodic series, like in the investigated monthly data case. It is used over hundreds of Consumer Price Index components to find similar dynamics and aggregate them by the similarity of their dynamics. Then aggregated series are given as input to the ARIMA, SARIMA, and LSTM models, to forecast the total Core Consumer Price Index. The choice is based on the necessity to capture possible non-linear relationships between series. The dataset is quite rich and contains hundreds of Consumer Price Index components, which is a level of prices for different goods. Data suffers from multiple issues, including seasonality, so controlling them either with satellite models such as X-12 or with the architecture of the forecasting model is sufficient. The research results are important for different groups of agents. Private businesses seek to plan their pricing while government structures want to employ their administrative measures in a proactive data-driven manner. The result shows that the SARIMA currently outperforms other models. An LSTM model combined with DTW + K-Means method shows worse results yet it was able to catch non-linearities, unlike more traditional models. Further investigation of LSTM + DTW/K-Means performance and fitting is necessary.

Pages of the article in the issue: 214 - 225

Language of the article: English


KRUKOVETS, D. (2020): Analysis of similarity between artificially simulated time series with Dynamic Time Warping. “Proceedings of Workshop on Intelligent Information Systems WIIS2020”, pp.97-108.

KRUKOVETS, D. (2022): Multi-stage approach with DTW and clustering for forecasting of average deposit rate in Ukraine. “Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics”, pp. 55-65.

KRUKOVETS, D. (2021): Dynamic Time Warping for uncovering dissimilarity of regional wages in Ukraine. “Proceedings MFOI-2020”, pp. 168-185.

KRUKOVETS, D., VERCHENKO, O. (2019): Short-run forecasting of core inflation in ukraine: a combined arma approach. “Visnyk of the National Bank of Ukraine 248”, pp. 1-10.

ALMOSOVA, A., ANDRESEN, N. (2019): Nonlinear Inflation Forecasting with Recurrent Neural Networks. “European Central Bank (ECB)”, pp. 1-45.

LONGO, L., RICCABONI, M., RUNGI, A. (2022): A neural network ensemble approach for GDP forecasting. “Journal of Economic Dynamics and Control”.

KRUKOVETS, D. (2020): Data science opportunities at central banks: overview. “Visnyk of the National Bank of Ukraine 249”, pp. 13-24.

EUROPEAN CENTRAL BANK (ECB) (2007): Guide to Seasonal adjustment with -12-ARIMA, March 2007, pp. 1-169.

THE COUNCIL OF THE NATIONAL BANK OF UKRAINE (2018): Monetary Policy Strategy Of The National Bank Of Ukraine, pp. 1-9.

TENREYRO, S. (2023): Macroeconomic stabilisation in a volatile inflation environment. “ECB forum on Central Banking”, pp. 1-37.

PROFATSKA, N. (2021): Standard quality report state statistical observation "changes in prices (tariffs) for consumer goods (services)" “State Statistics Service of Ukraine”, pp. 1-11.

STOCK, J., WATSON, M. (2019): Trend, Seasonal, and Sectoral Inflation in the Euro Area. “Princeton University”, pp.1-32.

SHAPOVALENKO, N. (2021): A Suite of Models for CPI Forecasting. “Visnyk of the National Bank of Ukraine”, pp. 252,4-36.

SIAMI-NAMINI, S., TAVAKOLI, N., SIAMI-NAMINI, A. (2018): A Comparison of ARIMA and LSTM in Forecasting Time Series. “17th IEEE International Conference on Machine Learning and Applications”, pp. 1-8.

KUMAR, M., THENMOZHI, M. (2014). Forecasting stock index returns using ARIMA- SVM, ARIMA-ANN, and ARIMA-random forest hybrid models. “International Journal of Banking Accounting and Finance” 5(3):284.

FAN, G., ZHANG, L., YU, M., HONG, W., DONG. S. (2022). Applications of random forest in multivariable response surface for short-term load forecasting. “International Journal of Electrical Power & Energy Systems”, Volume 139.

VALIPOUR, M. (2014): Long-term runoff study using SARIMA and ARIMA models in the United States. “Meteorol. Appl. 22”, pp. 592–598.

HYNDMAN, R., KHANDAKAR, Y. (2008): Automatic Time Series Forecasting: The forecast Package for R. “Journal of Statistical Software”, 27(3), pp. 1-22.

SHERSTINSKY, A. (2018): Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network. “Cornell University”, pp. 1–43.

GIORGINO, T. (2009): Computing and Visualizing Dynamic Time Warping Alignments in R: The dtw Package. “Journal of Statistical Software”, 31(7), pp. 1–24.

SALVADOR, S., CHAN, PH. (2007): Toward accurate dynamic time warping in linear time and space. “Intelligent Data Analysis”, 11(5), pp. 561-580.




How to Cite

Krukovets, D. (2023). Updated DTW+K-Means approach with LSTM and ARIMA-type models for Core Inflation forecasting. Bulletin of Taras Shevchenko National University of Kyiv. Physical and Mathematical Sciences, (2), 214–225. https://doi.org/10.17721/1812-5409.2023/2.38



Computer Science and Informatics