Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
IEEE Transactions on Knowledge and Data Engineering
| Hi-index | 0.00 |
The World Wide Web contains mostly unstructured textual information. Hence, with the growth of the Internet and the World Wide Web, the need for technology to analyze and mine textual information automatically is becoming increasingly important. We developed such a text mining system, which predicts daily closing values of major stock market indices in Asia, Europe, and America from financial news articles retrieved from the Web. Textual statements contain not only the effect (e.g., stocks went down) but also the possible causes of the event (e.g., stocks went down because of panicking investors). Exploiting textual information therefore increases the quality of the input. The forecasts are available daily via www.cs.ust.hk/ ~beat/Predict at 7:45 a.m. Hong Kong time. A simple trading strategy based on the predictions is presented and to be shown potentially more profitable than the actual index movements.