Deep Learning-Powered Business Analytics: Enhancing Classification and Regression Models

Trang Thi Huyen Cao, Huy Quoc Le () and Anh Ngoc Mai
Additional contact information
Trang Thi Huyen Cao: Hanoi University of Industry
Huy Quoc Le: Hanoi University of Industry
Anh Ngoc Mai: Academy of Finance

A chapter in Proceedings of the 5th International Conference on Research in Management and Technovation, 2025, pp 195-212 from Springer

Abstract: Abstract The data deluge demands businesses leverage artificial intelligence (AI) and machine learning (ML) for swift adaptation. Deep learning (DL), a powerful ML technique, unlocks deeper insights but faces limitations hindering its widespread adoption in business analytics. This article explores the key challenges of DL and emphasizes its role as a complementary tool, not a replacement, for traditional ML models. Research shows that DL models in classification tasks can perform quite well on structured datasets like powerful gradient boosting models. On the other hand, in prediction tasks, DL appears to be weaker compared to traditional ML models. In addition to experimental research based on four usage cases in the industry, the article also provides a comprehensive discussion of these results, their practical implications, and a roadmap for future research.

Keywords: Deep learning; Data-driven decision-making; Keras; Hyperparameters (search for similar items in EconPapers)
Date: 2025
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:prbchp:978-981-97-9992-3_13

Ordering information: This item can be ordered from
http://www.springer.com/9789819799923

DOI: 10.1007/978-981-97-9992-3_13

Access Statistics for this chapter

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