Parameter estimation in arima model with particle swarm optimization

Forecasting is an important problem for planning future. ARIMA models have been widely used for time series forecasting since 1970. There are maximum likelihood or least square methods to estimate parameters of ARIMA model. The ARIMA model is not linear in terms of its parameters when the model contain moving average terms and this model needs nonlinear optimization techniques for parameter estimation. In this study, a new algorithm is proposed employing particle swarm optimization for parameter estimation in ARIMA models. The performance of the proposed method is compared with some other methods by using real-world time series.