Stock Price Prediction Using Prior Knowledge and Neural Networks

@article{citeulike:2449920, abstract = {In this paper we investigate ways to use prior knowledge and neural networks to improve multivariate prediction ability. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events are into account. We have studied types of prior knowledge which are difficult to insert into initial network structures or to represent in the form of error measurements. We make use of prior knowledge of stock price predictions and newspaper information on domestic and foreign events. Event-knowledge is extracted from newspaper headlines according to prior knowledge. We choose several economic indicators, also according to prior knowledge, and input them together with event-knowledge into neural networks. The use of event-knowledge and neural networks is shown to be effective experimentally: the prediction error of our approach is smaller than that of multiple regression analysis on the 5\% level of significance. {\copyright} 1997 by John Wiley \& Sons, Ltd.}, address = {NTT Information and Communication Systems Laboratories, Tokyo, Japan; Takushoku University, Japan; NTT Information and Communication Systems Laboratories, Tokyo, Japan; Kyoto University, Japan}, author = {Kohara, Kazuhiro and Ishikawa, Tsutomu and Fukuhara, Yoshimi and Nakamura, Yukihiro }, citeulike-article-id = {2449920}, doi = {http://dx.doi.org/10.1002/(SICI)1099-1174(199703)6:1\%3C11::AID-ISAF115\%3E3.0.CO;2-3}, journal = {International Journal of Intelligent Systems in Accounting, Finance \& Management}, keywords = {ann, prediction, priorknowledge, stock}, number = {1}, pages = {11--22}, posted-at = {2008-03-01 02:59:13}, priority = {2}, title = {Stock Price Prediction Using Prior Knowledge and Neural Networks}, url = {http://dx.doi.org/10.1002/(SICI)1099-1174(199703)6:1\%3C11::AID-ISAF115\%3E3.0.CO;2-3}, volume = {6}, year = {1997} }

TY - JOUR ID - citeulike:2449920 L3 - citeulike-article-id:2449920 N2 - In this paper we investigate ways to use prior knowledge and neural networks to improve multivariate prediction ability. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events are into account. We have studied types of prior knowledge which are difficult to insert into initial network structures or to represent in the form of error measurements. We make use of prior knowledge of stock price predictions and newspaper information on domestic and foreign events. Event-knowledge is extracted from newspaper headlines according to prior knowledge. We choose several economic indicators, also according to prior knowledge, and input them together with event-knowledge into neural networks. The use of event-knowledge and neural networks is shown to be effective experimentally: the prediction error of our approach is smaller than that of multiple regression analysis on the 5% level of significance. © 1997 by John Wiley & Sons, Ltd. IS - 1 JF - International Journal of Intelligent Systems in Accounting, Finance & Management AD - NTT Information and Communication Systems Laboratories, Tokyo, Japan; Takushoku University, Japan; NTT Information and Communication Systems Laboratories, Tokyo, Japan; Kyoto University, Japan EP - 22 TI - Stock Price Prediction Using Prior Knowledge and Neural Networks VL - 6 SP - 11 KW - ann KW - prediction KW - priorknowledge KW - stock AU - Kohara, Kazuhiro AU - Ishikawa, Tsutomu AU - Fukuhara, Yoshimi AU - Nakamura, Yukihiro PY - 1997/// UR - http://dx.doi.org/10.1002/(SICI)1099-1174(199703)6:1%3C11::AID-ISAF115%3E3.0.CO;2-3 ER -