Optimization of smart choice of shares portfolio using artificial intelligence

In this paper, we present an approach for optimal portfolio choice. This approach is divided into two parts: The first part is to select from an initial portfolio, the relevants shares that have a positive influence on the return and risk portfolio using regression neural networks, i.e: The shares have a low risks and high returns. These shares will built a sub portfolio. In the second part, we seek the proportions that optimize these sub the portfolio whose risk used is semi-variance using genetic algorithms. This approach allows to achieve a financial gain in terms of cost reduction and tax. In addition, a reduction in computational load during the optimization phase.