Forecasting stock prices using a data mining method: Evidence from emerging market
研究了用决策树模型和CRISP-DM流程预测巴基斯坦股市十只股票价格，准确率在50%-60%之间，对投资者买卖决策有参考价值。
Abstract Stock price forecasting is considered a challenging task because of the various characteristics of financial time series. In this study, we attempt to predict stock prices using data mining techniques in an emerging market. The study uses decision tree model, CRISP‐DM (Cross‐Industry Standard Process for data mining) for analysis by employing WEKA software. The study sample consists of ten firms of five different sectors listed on Pakistan Stock Exchange (PSX). The findings show accuracy ratios range between 50% and 60%. The findings imply that market participants can disclose higher returns by considering information embedded in previous stock prices. In addition, investors can take more prudent buy‐sell decisions in view of our findings.