Back to Search Start Over

A novel artificial autonomous system for supporting investment decisions using a Big Five model approach.

Authors :
Cabrera-Paniagua, Daniel
Rubilar-Torrealba, Rolando
Source :
Engineering Applications of Artificial Intelligence. Feb2021, Vol. 98, pN.PAG-N.PAG. 1p.
Publication Year :
2021

Abstract

This paper presents the design of an artificial autonomous system (called AAS) for the stock market domain that considers an approximation from the Big Five model, which proposes that the personality of an individual belongs to one of five different personality profiles: openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several studies have explored investment and financial issues while considering the Big Five model, usually by analyzing data obtained from surveys applied to real people. However, to the best of our knowledge, there are no proposals that suggest the design of an AAS for supporting investment decisions that use the Big Five model as the central approach. The main objective of this proposal is to design an AAS for making investment decisions, where the decisions are adjusted to market conditions through the use of a policy function that adapts over time. This policy function adjusts the consumption level and investment portfolio composition required by the investment profile, considering both the market conditions and the Big Five model profile associated with the AAS. The effectiveness of the investment process is measured by observing the variations in the accumulated wealth and utility. The utility is measured through an abstract representation of the well-being or satisfaction of the investor (i.e., the AAS). AAS—Extraversion obtained the highest accumulated wealth, while AAS—Agreeableness obtained the highest level of utility, showing that the accumulated wealth is only one factor influencing the investor's well-being. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
09521976
Volume :
98
Database :
Academic Search Index
Journal :
Engineering Applications of Artificial Intelligence
Publication Type :
Academic Journal
Accession number :
147875910
Full Text :
https://doi.org/10.1016/j.engappai.2020.104107