The Arbitrage Pricing Theory and the Capital Asset Pricing Models and Artificial Neural Networks Modeling with Particle Swarm Optimization (PSO)

Abstract

We examine two stocks of Athens Exchange Stock Market, that of 'Coca-Cola' and 'Compucon'. We analyze the arbitrage pricing theory (APT) model and the Capital Asset Pricing Model (CAPM) and we compare the performance between them. Then we develop a neural network model in Synapse Software with the particle swarm optimization algorithm and show the flexibility of hybrid models and the Synapse software, as the superiority in forecasting performance, in relation to the traditional econometric methodology , like Ordinary least square and ARCH-GARCH estimations.