Behavioral finance is the study of how the psychology of investors affects personal investment and market outcomes. Based on investment behaviors, there is a need for investment dealerships and banks to develop tools that provide automated support for retail investors and financial advisors in selecting, managing, and evaluating investment portfolios. The difficulty in designing these tools lies in the specification of the complex mathematical structure that models investor behavior in the presence of market conditions. Machine learning offers a data-driven approach with less specification of the structure of the data generating process.
Financial industry has recently started using machine learning in personal finance applications, such as risk modelling, return forecasting, portfolio construction, financial distress prediction, and so forth. Growing in this body of work is using machine learning techniques to analyze retail investor trading behaviors. The growing interest is marked by a recent special issue titled “Artificial Intelligence for Behavioral Finance” in the Journal of Behavioral and Experimental Finance. The application of machine learning and AI in modelling investor behaviors is a natural partnership.
Understanding investor behaviors is paramount to each of these research areas, particularly in designing effective robo-tools for investors, advisors, dealerships, banks, and regulators. Particular interest lies in learning investor behaviors during the 2020 market crash informed by their previous behaviors. This workshop will bring together theoretical and industrial machine learners, quantitative finance experts, financial industry practitioners, and fintech entrepreneurs to share their understanding of how AI can be employed to better model investor behaviors, and guide the next steps in the research path of behavioral finance and machine learning.
We invite research papers on Machine Learning for Investor Modeling. The scope and topics include (broadly defined and not limited to):
Machine learning to model investor behaviors that are
informed by market events including news, social media, etc.,
guided by financial advisors with differing discretionary licenses, and
designed for use in Robo- and hybrid-advisor applications.
Sentiment analysis of investor and financial advisor communications using different datasets (phone calls, textual correspondence, or any other alternative data sources)
The role of AI/Decision Support Systems in Fintech designed to support retail investors in making better financial decisions.
Machine Learning for human, Robo, or hybrid financial advice and related areas.
Machine Learning for marketing and/or sales specifically for financial products/services, and related problems such as investor propensity, attrition, etc.
An intersection between behavioral finance and machine learning, broadly defined.
*‘Investors’ may be broadly defined starting from retail and institutional as well as financial advisors and brokers and any agent in the investment processes.
Overview of Industry Challenges
Short papers from financial industry practitioners that introduce domain specific problems and challenges to academic researchers. These papers should describe problems that can inspire new research directions in academia, and should serve to bridge the information gap between academia and the financial industry.
Algorithmic Tutorials
Short tutorials from academic researchers that explain current solutions to challenges related to the technical areas mentioned above, not necessarily limited to the financial domain. These tutorials will serve as an introduction and enable financial industry practitioners to employ/adapt latest academic research to their use-cases.
All submissions must be PDFs formatted in the Standard ACM Conference Proceedings Template (or, ACM LaTeX templates, use the sigconf template). Submissions are limited to 4-8 content pages, including all figures and tables but excluding references. All accepted papers will be presented as posters and some would be selected for oral presentations, depending on schedule constraints. Accepted papers will be posted on the workshop website.
Following the conference submission policy, reviews are double-blind, and author names and affiliations should NOT be listed.
Papers should be submitted on CMT3 by 13th September, 2022
Submission URL: https://cmt3.research.microsoft.com/MLIM2022/Submission/Index
Submission deadline: 13th September, 2022
Author notification: 19th September, 2022
Workshop: 2nd November, 2022 (1-5 pm)
Prof Matt Davison (Western University, Canada)
Dr Dhagash Mehta (BlackRock, Inc.)
Prof John RJ Thompson (University of British Columbia, Canada) (Primary Organizer)