Performance Evaluation of Iranian OTC's Companies by Using Stochastic Dominance Criteria and Optimizing with PSO and ANN Hybrid Model

The goal of the current study is performance evaluation of Iranian OTCs companies by using stochastic dominance and optimizing them by employing Artificial Neural Network and Particle Swarm Optimization hybrid model .To fulfill this objective, we used daily and weekly return of under investigation 36 companies of OTC During the period beginningfrom March 21, 2014 until March 20, 2015 in which the application of stochas tic dominance criteria for nonparametric orientation and proven performance of the hybrid model is particular interest. The research results indicated the first-order, second-order, and third-order dominances in the study companies. The portfolios were based on the shares of companies ranked with respect to the stochastic dominance criterion. Considering the minimum and maximum numbers of shares to be 2 and 10 for each portfolio, an eight-share portfolio was selected as the optimal portfolio with the combination of the activation function TPT. Compared with the index of Iran OTC during the research period, the selected portfolio indicated a significantly higher performance.