An Improved Genetic Algorithm for Selection of IT Investment Projects with a Portfolio Problem Approach
Manuel Tupia, Rony Cueva, Miguel Guanira · INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences · 2013
The decision to invest in one of the most critical activities within any business strategy and is usually based on the application of a set of economic and financial analytical tools and various other project evaluation techniques. Specifically when the nature of the investment includes issues related to information technologies (such acquisition, maintenance and development, etc.), unfavorable scenarios arise because it is considered that the above analytical instruments not properly applied to such projects. The indiscriminate use of information technology (IT) does not result in any benefit to the company: get value only if you choose the one that works best for IT in terms of efficiency, higher rates of profit, as well as cost reduction in intended withstand processes. This paper shows an application of bio-inspired and evolutionary computing, which is characterized in simulation techniques using living things to survive and evolve in nature, such as genetic algorithms. With this tool will seek to resolve the selecting investment projects problem, as a variant of the well-know portfolio problem. Genetic algorithms are based on simulating the concepts of inheritance, chromosomal representation, natural selection and evolutions, making possible combinations for converge to optimal solutions.