Genetic forecasting algorithm with financial applications

A new forecasting algorithm using features of genetic algorithms (GAs) is proposed. The algorithm combines the powerful search of GAs and their capability to learn pattern relationships of past data in order to forecast future values. The genetic forecasting algorithm consists of two steps: forecasting and learning. GAs are used in the forecasting step to estimate parameters of the problem domain. Pattern learning is taken into account in the algorithm to capture the pattern relationships of learning data. The results of the algorithm are examined by applying them in two financial problem domains: commercial bank deposit and bankruptcy prediction