Building an efficient investment portfolio using neural networks – an analytical study in a sample of companies listed in the Iraq Stock Exchange

Abstract

The research aims to create a systematic and comprehensive framework for building an efficient investment portfolio using statistical and mathematical modelling techniques, in a way that contributes to improving the investment decision-making process and increasing investor returns while reducing the associated financial risks, as well as providing a deep understanding of the dynamics of financial markets through historical data analysis. In this study, companies were limited to the research community, with 71 companies from different sectors. These companies were selected based on a set of conditions, namely (company size, sector to which the company belongs, trading and liquidity, continuity and continuous listing, continuous financial performance, historical financial performance) for the years (2021-2023-2023). The researcher reached an important conclusion, which is that the use of neural networks in building an efficient investment portfolio can contribute to increasing the efficiency of this investment portfolio, in a way that positively reflects on achieving the investor's goals by achieving the best balance between investment portfolio returns and risks, and allocating funds more efficiently, as well as improving the accuracy of expectations about the returns of companies' stocks. Accordingly, investment companies and institutions should delve deeper into using