以文件分類技术预测股价趋势.PDF

類 Predicting Trends of Stock Prices with Text Classification Techniques Jiun-Da Chen Tai-Ping Wang 劉麟 Chao-Lin Liu 立 理理 立 Department of Department of Department of Computer Science Information Management Computer Science National Chengchi University Aletheia University National Chengchi University g9414@.tw tpwang@.tw chaolin@.tw 不 不 來更 略 類來 類易k 了類料度 料度來類 率類異 利類類 類良行參 Abstract Stocks closing price levels can provide hints about investors aggregate demands and aggregate supplies in the stock trading markets. If the level of a stocks closing price is higher than its previous closing price, it indicates that the aggregate demand is stronger than the aggregate supply in this trading day. Otherwise, the aggregate demand is weaker than the aggregate supply. It would be profitable if we can predict the individual stocks closing price level. For example, in case that one stocks current price is lower than its previous closing price. We can do the proper strategies(buy or sell) to gain profit if we can predict the stocks closing price level correctly in advance. In this paper, we propose and evaluate three models for predicting individual stocks closing price in the Taiwan stock market. These models include a naïve Bayes model, a k-nearest neighbors model, and a hybrid model. Experimental results show the proposed methods perform better than the NewsCATS system for the UP and DOWN categories. 易k Keywords: Stock Price Prediction, naïve Bayesian models, kNN models, hybrid models. 論 令 [11]來 [6][8][12] 不歷 料來來不 度… 易來 料來 更略 量略易 力量更了 略參 [13][14][17][18][21] 料[15] 行理 料 [14][17][21] 類來 行 率類異 行參 來 料類來 易 行參 不類來 立易 k 料理 來行類來料 類類行 料練料料兩類利練料來練類 料來類料 類來 行