Application of machine learning algorithms in economic analysis

This article explores the application of machine learning algorithms in economic sciences, focusing on data analysis, forecasting, and risk management. These tasks require high computational accuracy and large-scale data processing, making classical systems time-consuming and costly. The study highl...

Full description

Saved in:
Bibliographic Details
Main Author: Mohammad Sadegh SALEM
Format: Article
Language:English
Published: General Association of Economists from Romania 2024-05-01
Series:Theoretical and Applied Economics
Subjects:
Online Access: https://store.ectap.ro/suplimente/Theoretical_and_Applied_Economics_2024_Special_Issue_Autumn.pdf#page=129
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article explores the application of machine learning algorithms in economic sciences, focusing on data analysis, forecasting, and risk management. These tasks require high computational accuracy and large-scale data processing, making classical systems time-consuming and costly. The study highlights the role of cloud computing in overcoming these challenges by offering scalable resources and enhanced computational power. Cloud-based machine learning can increase the speed and efficiency of economic analysis, outperforming traditional methods. The research follows a library study methodology to identify key computational challenges in economics and how cloud-based machine learning can provide superior solutions. The study aims to show that cloud computing enables faster and more accurate economic forecasting, particularly in areas like income management and risk analysis. Additionally, the article investigates the short-term feasibility of implementing cloudbased machine learning methods and raises questions about how this approach can improve the accuracy and speed of economic analyses. The findings suggest that cloud computing is a viable alternative to classical methods in addressing complex economic problems, offering significant advantages in financial resource management and risk analysis.
ISSN:1841-8678
1844-0029