We incorporate advanced higher moments of individual or institutional investors in a new approach dealing with the portfolio selection problem, formulated under a multi-criteria optimization framework. The “integrated portfolio intelligence” model extracts hidden patterns out of company fundamental indices and filters out effects such as trader noise or fraud utilizing advanced big data machine learning modeling. One of the main advantages of this novel system aside from providing with computer-efficient algorithmic optimality and predictive out performance is that it detects and extracts hidden trader behavioral patterns and firm investment “styles” from the data sets of large-scale institutional portfolios, which ultimately leads to the aversion and protection of extensive market manipulation and speculation.
Portfolio Optimization With Investor Utility Preference of Higher-Order Moments: A Behavioral Approach
We would like to thank the Editor, Professor Barkley Rosser for helpful feedback as well as two anonymous referees. We are grateful to faculty members at the Economics Department of the European University Institute (EUI) as well as seminar participants at various institutions for valuable discussions. The first author has received funding from the EU Horizon 2020 research and innovation programme under the MS-C Grant No 656136. The usual disclaimers apply.
Bekiros S, Loukeris N, Eleftheriadis I (2017), "Portfolio Optimization With Investor Utility Preference of Higher-Order Moments: A Behavioral Approach". Review of Behavioral Economics, Vol. 4 No. 2 pp. 83–106, doi: https://doi.org/10.1561/105.00000060
Download citation file:
Sign in
ICE Member Sign In
Log inPurchased this content as a guest? Enter your email address to restore access.
