Thesis (M.Sc.) - Cairo University - Faculty of Computers and Information - Department of Computer Science

Who would have thought that birds or organisms could shape our trading decisions in the financial markets? Trading robots, being responsible for analyzing the financial markets and automating, without any human discretionary intervention, the trade decisions, executions, and management are interdisciplinary. Looking for that deep-seated element, which is essential in the development of nearly every trading system, led to optimization, and so it was selected as the principal objective of this research. Eight novel optimization techniques of the most recent contributions to metaheuristics, that is, Bat Algorithm (BA), Cuckoo Search (CS), Differential Search (DS), Firefly Algorithm (FA), Gravitational Search Algorithm (GSA), One Rank Cuckoo Search (ORCS), Separable Natural Evolution Strategy (SNES), and eXponential Natural Evolution Strategy (xNES) had their performance investigated. The top performers have been selected for further study on three algorithmic trading systems to verify their performance in this arena. The genetic algorithm (GA), as the dominant actor in the area of algorithmic trading systems optimization, has been included to serve as a benchmark to evaluate the results of the selected algorithms. The obtained results advocated a promising success for three of the selected optimization techniques, namely the CS, DS, and ORCS algorithms. These top performing techniques were inspired by the characteristic behaviors of cuckoo birds and superorganisms

Issued also as CD