An Unsupervised Neural Network for Stock Prediction

摘要：

The unsupervised Kohonen Networks equipped with Short Term Memory and Random Walk Breakout are used with straight-line equation, as the curve fitting algorithm to predict the stock prices. According to the results obtained, the unsupervised networks do not have that high accuracy of prediction in general because of the constraint on the fixed number of patterns that they can recognize. However, they provide the fastest time output and thus are very useful in time critical situations.

作者: Tony Kai Yun Chan Chong Tan Neeraj Haralalka

作者单位: School of Computer Engineering, Nanyang Technological University,Nanyang Avenue, Singapore 639798, Singapore

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 806-809

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）