Parameter estimation with particle swarm optimization in Holt's linear trend method

Holt's linear trend method is a simple method to solve time series which have linear trend. Although Holt's linear trend method is simple, it can produce successful forecasting results. Estimating smoothing parameters and initial values of trend and level directly effects to forecasting performance. In this study, performance of particle swarm optimization for simultaneously estimation of smoothing parameters and initial values of trend and level is investigated.