Generating Synthetic Data to Test Financial Strategies and Investment Products for Regulatory Compliance

10 Pages Posted: 14 Mar 2019 Last revised: 20 Mar 2019

See all articles by J.B. Heaton

J.B. Heaton

J.B. Heaton, P.C.

Jan Witte

University College London - Department of Mathematics

Date Written: March 15, 2019

Abstract

Regulations require investment professionals to decide whether financial products and investment strategies are in the best interest of investors, prudent investments, or suitable for customers and clients. This requires an understanding of potential risks and returns which in turn requires assumptions about future price behavior. Historical financial-market data alone provides too shaky a foundation for these assumptions, because financial advice can depend too heavily on anomalies, creating risks of legal and regulatory liability. We explain how to generate and use synthetic data to address this problem. Well-constructed synthetic data promises better best-interest, prudence, and suitability decisions for investment advisers, fiduciaries, and broker-dealers and better financial outcomes for investors.

Keywords: Synthetic Data, Machine Learning, Suitability, Best Interest, Compliance

Suggested Citation

Heaton, J.B. and Witte, Jan, Generating Synthetic Data to Test Financial Strategies and Investment Products for Regulatory Compliance (March 15, 2019). Available at SSRN: https://ssrn.com/abstract=3340018 or http://dx.doi.org/10.2139/ssrn.3340018

J.B. Heaton (Contact Author)

J.B. Heaton, P.C. ( email )

20 West Kinzie
17th Floor
Chicago, IL 60654
United States
(312) 487-2600 (Phone)

HOME PAGE: http://jbheaton.com

Jan Witte

University College London - Department of Mathematics ( email )

Gower Street
London, WC1E 6BT
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
38
Abstract Views
192
PlumX Metrics