Daily Prediction of Major Stock Indices from Textual WWW Data

We predict stock markets using information containedin articles published on the Web. Mostly textual articles appearingin the leading and the most influential financial newspapersaretakenas input. From those,articlesthe daily closingvaluesof major stockmarketindicesin Asia,Europe and America are predicted.Textual statementscontain not only the effect (e.g., stocks down) but also the possible causesof the event (e.g.,stocksdown becauseof weakness in the dollar and consequentlya weakeningof the treasury bonds). Exploiting textual information therefore increases the quality of the input. The forecastsareavailablereal-time via www.cs.ust.hk/-beat/Predictdaily at 7:45 am Hong Kong time. Hence all predictions are available before the major Asian marketsstart trading. Severaltechniques,such as rule-based,k-NN algorithm and neural net, have been employed to produce the forecasts.Those techniquesare comparedwith oneanother.A trading strategybasedon the system'sforecastis suggested.

• Type: Conference
• Year: 1998
• Where: KDD
• Authors: Beat Wüthrich, D. Permunetilleke, S. Leung, Vincent Cho, Jian Zhang, W. Lam
• Keywords: Closingvaluesof Major Stockmarketindicesin, Data Mining, E.g., KDD 1998, Stocksdown Becauseof Weakness