A new hybrid for improvement of auto-regressive integrated moving average models applying particle swarm optimization

摘要: A time series forecasting is an active research applied significantly in a variety of economics areas. Over the past three decades auto-regressive integrated moving average (ARIMA) model, as one most important models, has been financial markets forecasting. Recent researches ARIMA models indicate some basic limitations which detract from their popularities for forecasting: One limitation model that it requires large amount historical data to generate accurate result. Both theoretical and empirical findings suggest combining different may be effective method improving predictive performances especially when ensemble are quite different. The main purpose present paper combine with particle swarm optimization (PSO) order improve more results. Under small information, PSO performs better performance results compared itself. proposed robust used alternative tool