Prediction of economic benefits of market digital transformation based on federal learning algorithm

Lu Zhang, Wanqing Chen and Hengzhi Nie

International Journal of Sustainable Development, 2023, vol. 26, issue 3/4, 190-205

Abstract: In order to solve the problems of low prediction accuracy and long prediction time existing in traditional methods for predicting the economic benefits of market digital transformation, a method for predicting the economic benefits of market digital transformation based on federal learning algorithm is proposed. Obtain the prediction indicators and build a prediction indicator system for the economic benefits of market digital transformation. Pre-process the indicator data using the principal component analysis method, build a sample dataset, build a federal optimisation algorithm using the random gradient descent method, establish a minimum loss function, build a prediction model for the economic benefits of market digital transformation, and output the prediction results. The experimental results show that the prediction accuracy of the proposed method can reach more than 95%, and the prediction time is always kept within 3 s, with good prediction effect and efficiency.

Keywords: federated learning algorithm; digital transformation of the market; economic performance; principal component analysis; random gradient descent method. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=134419 (text/html)
Access to full text is restricted to subscribers.

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:ids:ijsusd:v:26:y:2023:i:3/4:p:190-205

Access Statistics for this article

More articles in International Journal of Sustainable Development from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().