Stochastic multi criteria decision analytics and artificial intelligence in continuous automated trading for wealth maximization
Date of Original Version
Recent technological and regulatory advances have coalesced to usher in an era where both automated and algorithmic trading routinely characterize a wealth maximization process managed by the continuous trading of equity securities. Under this approach to wealth maximization, automated trading focuses on the process determining directional trades for individual securities based upon the receipt and interpretation of new data. This paper presents a stochastic price formation algorithm that implements a cognitive decision making system modeled by twin radial basis function artificial neural networks to produce a high frequency automated trading system for individual equity securities listed on U.S. exchanges. The overall effectiveness and efficiency of the automated trading system is calibrated by estimating non-parametric quasi elasticity coefficients for individual firm fundamental characteristics. We find that automation driven by cognitive science can effectively auto-trade securities and produce changes to individual wealth that equals or exceeds the performance generated by a simple buy-and-hold strategy. We also identify four fundamental firm factors that explain the ability of the automated trading algorithm to produce a measured level of percent-positive trades. © Izmir University of Economics, Turkey, 2010.
24th Mini EURO Conference on Continuous Optimization and Information-Based Technologies in the Financial Sector, MEC EurOPT 2010
Dash, Gordon H., Nina Kajiji, and John Forman. "Stochastic multi criteria decision analytics and artificial intelligence in continuous automated trading for wealth maximization." 24th Mini EURO Conference on Continuous Optimization and Information-Based Technologies in the Financial Sector, MEC EurOPT 2010 , (2010): 288-293. https://digitalcommons.uri.edu/cba_facpubs/439