Cash flow prediction using artificial neural network and GA-EDA optimization

Abstract

Cash flow models are one of the spotlights for evaluating a project. The actual data should be modeled then it could be used for the prediction process. In this paper, 996 airplane maintenance basis data are used as a database, and 119 similar data are chosen after clustering. The project is divided into 20 equal periods and first three periods are used for simulating the next point. The predicted data for each point is achieved by using of previous points from the beginning. The model is based on artificial neural network, and it is trained by three algorithms which are Genetic Algorithm (GA), Estimation of Distribution Algorithm (EDA), and hybrid GA-EDA method. Two dynamic ratios are used which are dividing the population into two halves, and the other is a ratio without dividing. The ratio would give a proportion to GA and EDA models in the hybrid algorithm, and then the hybrid algorithm could model the system more accurately. For each algorithm, three main errors are calculated which are mean absolute percentage error (MAPE), mean square error (MSE), and root means square error (RMSE). The best result is achieved for hybrid GA-EDA model without dividing the population and the MAPE, RMSE, and MSE values are %0.022, 28944.59 Dollars, and 837789503.79 Dollars, respectively.