An Economic Model Processing Noise Method Based on Clustering in the Post-Epidemic Era

Tengyao Tu ()
Additional contact information
Tengyao Tu: University of Bristol, School of Engineering Mathematics and Technology

A chapter in Proceedings of the 9th International Conference on Financial Innovation and Economic Development (ICFIED 2024), 2024, pp 202-213 from Springer

Abstract: Abstract Since the 21st century, the world economic situation has undergone complex changes. Macroeconomic forecasting has become a hot topic of research for many scholars. An accurate macroeconomic forecast is of great significance to the country, enterprises, and individuals. However, in the post-pandemic era, some scholars have simply chosen all datasets for predicting macroeconomics. But, as the impact of the epidemic gradually decreases and the macroeconomic situation gradually returns to normal, the economic data on the impact of the epidemic is noisy. The article uses TOPSIS scoring to discuss the extent to which the UK’s macroeconomy has been affected after the outbreak of the epidemic, quantify the impact of the epidemic on the economic sector, and cluster the affected and unaffected intervals using clustering algorithms. We find that the period from Q1 2020 to Q1 2022 is the range of the impact of COVID-19 on the macro-economy. Moreover, the second quarter of 2020 is the period when COVID-19 has the greatest impact on the macro-economy. And the data after Q1 2022 is in the low-impact area, which is the post-pandemic period. At the same time, we compared macroeconomic volume prediction methods using different datasets. When the impact of the epidemic on the economic volume was significant and intuitive, the model that excluded data from the epidemic period showed a significant performance improvement compared to the model with a complete dataset. When the impact of the epidemic on the economic quantity is not intuitive, removing data from the epidemic period will also improve the effectiveness of the model.

Keywords: Macroeconomics; Outlier; TOPSIS; K-means; Regression (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-408-2_24

Ordering information: This item can be ordered from
http://www.springer.com/9789464634082

DOI: 10.2991/978-94-6463-408-2_24

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().