New Trend in Fintech: Research on Artificial Intelligence Model Interpretability in Financial Fields - Open Journal of Applied Sciences

OJAppS > Vol.9 No.10, October 2019

Open Journal of Applied Sciences

Volume 9, Issue 10 (October 2019)

ISSN Print: 2165-3917 ISSN Online: 2165-3925

Google-based Impact Factor: 1 Citations

New Trend in Fintech: Research on Artificial Intelligence Model Interpretability in Financial Fields ()

HTML XML

Download as PDF (Size: 814KB) PP. 761-773

DOI: 10.4236/ojapps.2019.910062 1,559 Downloads 3,706 Views Citations

Author(s)

Han Yan^1,2, Sheng Lin^1,2,3

Affiliation(s)

¹International Institute of China Construction Bank, Beijing, China.
²Postdoctoral Workstation of China Construction Bank, Beijing, China.
³Guangzhou Digital Finance R&D Business Group of China Construction Bank Fintech, Guangzhou, China.

ABSTRACT

With the development of Fintech, applying artificial intelligence (AI) technologies to the financial field is a general trend. However, there are some inappropriate conditions, for instance, the AI model is always treated as a black box and cannot be interpreted. This paper studies the AI model interpretability when the models are applied in the financial field. We analyze the reasons of black box problem and explore the effective solutions. We propose a new kind of automatic Regtech tool—LIMER, and put forward policy suggestions, thereby continuously promoting the development of Fintech to a higher level.

KEYWORDS

Fintech, Regtech, AI, Model Interpretability, LIMER

Share and Cite:

Yan, H. and Lin, S. (2019) New Trend in Fintech: Research on Artificial Intelligence Model Interpretability in Financial Fields. Open Journal of Applied Sciences, 9, 761-773. doi: 10.4236/ojapps.2019.910062.

Cited by

[1]	Test input prioritization for Machine Learning Classifiers
	IEEE Transactions …, 2024

[2]	A comprehensive review on financial explainable AI
	arXiv preprint arXiv …, 2023

[3]	On the Black-Box Challenge for Fraud Detection Using Machine Learning (II): Nonlinear Analysis through Interpretable Autoencoders
	Ulldemolins, FJ Gimeno-Blanes… - Applied Sciences, 2022

[4]	On the Black-Box Challenge for Fraud Detection Using Machine Learning (I): Linear Models and Informative Feature Selection
	Ulldemolins, FJ Gimeno-Blanes… - Applied Sciences, 2022

[5]	Machine Learning Interpretable para la detección del fraude crediticio
	2022

Journals Menu

Follow SCIRP

	customer@scirp.org
	+86 18163351462(WhatsApp)
	1655362766

	Paper Publishing WeChat

Journals Menu

Home

About SCIRP

Service

Policies