Creating Powerful and Interpretable Models with Regression Networks

Lachlan O'Neill (), Simon Angus (), Satya Borgohain (), Nader Chmait () and David Dowe ()
Additional contact information
Lachlan O'Neill: Faculty of Information Technology, Monash University
Satya Borgohain: SoDa Laboratories, Monash Business School, Monash University
Nader Chmait: Faculty of Information Technology, Monash University
David Dowe: Faculty of Information Technology, Monash University

No 2021-09, SoDa Laboratories Working Paper Series from Monash University, SoDa Laboratories

Abstract: As the discipline has evolved, research in machine learning has been focused more and more on creating more powerful neural networks, without regard for the interpretability of these networks. Such “black-box models†yield state-of-the-art results, but we cannot understand why they make a particular decision or prediction. Sometimes this is acceptable, but often it is not. We propose a novel architecture, Regression Networks, which combines the power of neural networks with the understandability of regression analysis. While some methods for combining these exist in the literature, our architecture generalizes these approaches by taking interactions into account, offering the power of a dense neural network without forsaking interpretability. We demonstrate that the models exceed the state-of-the-art performance of interpretable models on several benchmark datasets, matching the power of a dense neural network. Finally, we discuss how these techniques can be generalized to other neural architectures, such as convolutional and recurrent neural networks.

Keywords: machine learning; policy evaluation; neural networks; regression; classification (search for similar items in EconPapers)
JEL-codes: C14 C45 C52 (search for similar items in EconPapers)
Date: 2021-09
New Economics Papers: this item is included in nep-big, nep-cmp, nep-ecm and nep-isf
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://soda-wps.s3-website-ap-southeast-2.amazonaw ... r/sodwps/2021-09.pdf (application/pdf)

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:ajr:sodwps:2021-09

Ordering information: This working paper can be ordered from
https://www.monash.edu/business/soda-labs/home

Access Statistics for this paper

More papers in SoDa Laboratories Working Paper Series from Monash University, SoDa Laboratories SoDa Laboratories, Monash University, Victoria 3800, Australia. Contact information at EDIRC.
Bibliographic data for series maintained by Ashani Amarasinghe ( this e-mail address is bad, please contact ).