Multicriteria interpretability driven deep learning

Marco Repetto ()
Additional contact information
Marco Repetto: Siemens Italy, Digital Indutries

Annals of Operations Research, 2025, vol. 346, issue 2, No 33, 1635 pages

Abstract: Abstract Deep Learning methods are well-known for their abilities, but their interpretability keeps them out of high-stakes situations. This difficulty is addressed by recent model-agnostic methods that provide explanations after the training process. As a result, the current guidelines’ requirement for “interpretability from the start” is not met. As a result, such methods are only useful as a sanity check after the model has been trained. In an abstract scenario, “interpretability from the start” implies imposing a set of soft constraints on the model’s behavior by infusing knowledge and eliminating any biases. By inserting knowledge into the objective function, we present a Multicriteria technique that allows us to control the feature effects on the model’s output. To accommodate for more complex effects and local lack of information, we enhance the method by integrating particular knowledge functions. As a result, a Deep Learning training process that is both interpretable and compliant with modern legislation has been developed. Our technique develops performant yet robust models capable of overcoming biases resulting from data scarcity, according to a practical empirical example based on credit risk.

Keywords: Artificial intelligence; Machine learning; Deep learning; Multiple objective programming; Multicriteria optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10479-022-04692-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:annopr:v:346:y:2025:i:2:d:10.1007_s10479-022-04692-6

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-022-04692-6

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().