Experimental analysis of stock market using stock price prediction model with Kalman Filter

The authors analyzed the Tokyo stock market using individual daily stock price data between Feb. 6, 1988 and Oct. 24, 1989. A combination of the factor model and the AR model is used to fit the data. The authors consider the data in terms of a State-Space model, so that the Kalman Filter is used to estimate the model. The estimated model was used for both explanation and prediction of the individual stock price data. The authors found that our model reduced the prediction error compared with the MTV and the usual one-dimensional AR model.