Title:
MACHINE-LEARNING TECHNIQUES FOR FACTOR-LEVEL MONOTONIC NEURAL NETWORKS
Document Type and Number:
WIPO Patent Application WO/2022/020162
Kind Code:
A3
Abstract:
In some aspects, a computing system can generate and optimize a neural network for risk assessment. Input predictor variables can be analyzed to identify common factors of these predictor variables. The neural network can be trained to enforce a monotonic relationship between each common factor of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under this monotonic constraint. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.
Inventors:
TURNER MATTHEW (US)
MILLER STEPHEN (US)
MILLER STEPHEN (US)
Application Number:
PCT/US2021/041681
Publication Date:
March 03, 2022
Filing Date:
July 14, 2021
Export Citation:
Assignee:
EQUIFAX INC (US)
International Classes:
G06N3/04; G06N3/08; G06N5/00
Foreign References:
| AU2016428862A1 | 2019-06-27 | |||
| US20200134439A1 | 2020-04-30 |
Other References:
SILVA WILSON ET AL: "How to produce complementary explanations using an Ensemble Model", 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), IEEE, 14 July 2019 (2019-07-14), pages 1 - 8, XP033622246, DOI: 10.1109/IJCNN.2019.8852409
AKHIL GUPTA ET AL: "How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 September 2019 (2019-09-24), XP081543748
AKHIL GUPTA ET AL: "How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 September 2019 (2019-09-24), XP081543748
Attorney, Agent or Firm:
GARDNER, Jason D. et al. (US)
Download PDF: