An agent-based approach for predictions based on multi-dimensional complex data

This paper presents an agent-based approach to the identification of prediction models for continuous values from multi-dimensional data, both numerical and categorical. A simple description of the approach is: a number of agents are sent to the data space to be investigated; at the micro-level, every agent tries to build a local linear model with multi-linear regression by competing with others, and then at the macro-level all surviving agents build the global model by introducing membership functions. Three tests were carried out and the performance of the approach was compared with a neural network. The results of the three tests show that the agent-based approach can have good performance for some data sets. The approach complements rather than competes with existing Soft Computing methods.