CHALLENGES AND PROBLEMS IN TODAY'S ECONOMIC FORECASTS

Georgi Georgiev, Vladislava Georgieva

Abstract


The purpose of the publication is to present to the academic community and practitioners in our country the achieved forecast accuracy in the economic field by applying various modern methods. The main challenges and problems related to time series forecasting and the adequacy of the forecasting models are considered.


Keywords


time series forecasting, symmetric mean absolute percentage error, machine learning, forecasting model adequacy, overfitting, underfitting

Full Text:

PDF

References


Ahmed N., Amir F. Atiya, H. El-Shishiny, An Empirical Comparison of Machine Learning Models for Time Series Forecasting, Econometric Reviews, Volume 29, 2010.

Bontempi G., S. Ben Taieb, and Y. Le Borgne, Machine Learning Strategiesfor Time Series Forecasting, Springer-Verlag, Berlin Heidelberg, 2013.

Everitt B.S., Skrondal A. Cambridge Dictionary of Statistics, Cambridge University Press 2010.

Makridakis Spyros, The Contributions of the M4 Competition to the Theory and Practice of Forecasting, 2019.

Makridakis S., E. Spiliotis , V. Assimakopoulos, Statistical and Machine Learning forecasting methods: Concerns and ways forward, 2018.

Montgomery D. , Ch. Jennings and M. Kulahci, Introduction to Time Series Analysis and Forecasting, John Wiley & Sons. Inc .. Hoboken. New Jersey, 2008.

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0194889

https://doi.org/10.1371/journal.pone.0194889.t008

www.mcompetitions.unic.ac.cy

https://forecasters.org/resources/time-series-data/m3-competition


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.