Abstract: Prediction is a behavior which describes the development of the future based on the regularity identified from the past data in a certain period of time.In recent years,the prediction is used in a lot of domains,such as electricity price forecasts,stock prices and weather forecasts.However,the traditional forecasting methods are unable to meet the needs of today’s forecast demand because their accuracy is not high enough or speed is not fast enough.Based on the idea of combination forecasting,the study proposed a combination forecasting algorithm using gray prediction model and extreme learning machine as a weighted method which determines the weights based on the cumulative function in the reinforcement learning for the problem of traditional forecasting methods.Three datasets,including Microsoft stock price,Mackey-Glass time-series data and Taiwanese color filter manufacturing data,were evaluated in the experiment.The results show that the proposed method is effective.

Key words: Forecasting,Combination forecasting,Grey prediction,Extreme learning machine,Gray extreme learning machine