K. Kamijo and T. Tanigawa. Stock price pattern recognition - a recurrent neural network approach. In 1990 International Joint Conference on Neural Networks, pages I215--222, 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....over previous work in this area in the following aspects: 1. It provides a high level platform upon which analysts can define and search patterns easily without much programming expertise; this is di#erent from works in neural network which treat the pattern discovery process as a black box [12] something that the user can be uncomfortable with. 2. Its specification is close to how analysts would describe the patterns in human terms, but without compromising on precision. 3. It allows to define new technical indicators and use them in pattern definitions to specify constraints. This ....

K. Kamijo and T. Tanigawa. Stock price pattern recognition - a recurrent neural network approach. In 1990 International Joint Conference on Neural Networks, pages I215--222, 1990.

....accuracies of 88.3 versus 64.7 were achieved, respectively. Odom and Sharda [1990] looked at bankruptcy prediction using discriminant analysis and neural networks. Their results gave the edge to the ANN by a 77.8 to 70.4 margin. In another instance, involving stock price pattern recognition, Kamijo Tanigawa [1990] developed an ANN which recognized the correct pattern in 15 of 16 cases studied (93.8 correct) The forecasting system of Kimoto and Asakawa [1990] was able to achieve an 18.6 greater profit trading the TOPIX index on the Tokyo Exchange compared with a traditional buy and hold strategy. ....

Kamijo, K. and Tanigawa, T. [1990] "Stock Price Pattern Recognition: A Recurrent Neural Network Approach," Proc. of the IJCNN, San Diego, Ca, pp. 215-221.

....drawbacks that this paper investigates. There has been work done on neural networks for prediction of time series [11, 19, 28, 31] as well as studies of using neural networks for predicting financial phenomena, such as currency exchange [26, 38] bond ratings [7, 30] and stock prices [15, 16, 27, 37]. This body of research in mainly centered on sequential prediction using indicator data, usually in known and large amounts. More pertinent to the use of neural networks for cost estimation is the research directed at neural networks as surrogates for regression. Probably the most fundamental ....

K. Kamijo and T. Tanigawa, "Stock price pattern recognition - a recurrent neural network approach," Proceedings of the 1990 International Joint Conference on Neural Networks, I215 -222, 1990.

.... ffl(t) 28) s(t) F 2 ( s(t Gamma 1) j(t) 29) Like in the previous sections on non linear ARMA models, these non linear functions F 1 and F 2 could be modeled by an MLP or RBFN, as well. The resulting network is depicted in figure 7. An example of the application of such a network is [27]. 6.1 Multi recurrent networks [46] and [47] has given an extensive overview of additional types of recurrencies, time windows and time delays in neural networks. By combining several types of feedback and delay one obtains the general multirecurrent network (MRN) depicted in figure 8. First, ....

Kamijo K., Tanigawa T.: Stock Price Pattern Recognition: A Recurrent Neural Network Approach, in Trippi R.R. & Turban E.(eds.): Neural Networks in Finance and Investing, Probus, Chicago, pp.357-370, 1993.

No context found.

Kamijo, K.-I., and T. Tanigawa (1990), "Stock Price Pattern Recognition: A Recurrent Neural Network Approach," Proceedings of the IEEE International Joint Conference on Neural Networks, pp. 1215-1221.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC