Abstract: This paper deals with identification of subset autoregressive time series model. The motivation of this paper is to solve the problem of "combinational explosion" which results from determination of the optimal subset of regression terms. By using simulated annealing, an approach for optimizing the subset is introduced for this pur-pose.
The proposed algorithm is applied for modeling and prediction of monthly death rate in the population. The results show the effectiveness of the method,

Key words: subset autoregressive (SSAR) model, simulated annealing, identification