Forming of the investment portfolio using self organizing neural networks

Abstract

The problem of comparison of different companies is facing, when looking for possible candidates for the investment portfolio. Screening of the companies, using “well-known” trading strategy parameters, is one of the ways to solve this problem. Actually, much more companies appear on the list, than the trader is willing to buy. To define the best companies or group of the best companies self-organizing (Kohonen's) neural network could be used. Using fundamental financial parameters as inputs, the output of neural network forms the different groups of companies located into a number of disjoint clusters. Then, by the special averaging technique, the 3D map of quality of investment could be formed. Investing portfolios could be formed by simple technical analysis approach. Non-linear ranging technique was applied as an alternative to self-organizing neural network procedure. The certain meanings of weights were given to the factors, which characterize the companies. Then, by estimation of all weights, companies were assigned to their place in the general listing. Four different portfolios were formed as a result of these researches. The performance of these portfolios showed which of the researched techniques gave better result. The real data from USA stock markets was used for the realization of the whole idea.