- 期刊
Prediction of DJIA based on Machine Learning and Natural Language Processing
摘要
This work harnessed news headlines in a machine leanring and natural language processing framework to predict the DJIA up and down moves. Several finding will be showed as follow 1) News headlines contribute to the accuracy of predictions. 2) The Twitter sentiment does not drive the accuracy of stock market predictions. 3) There are differences in the results of the stock market forecast using different models.
參考文獻
Fama, E. F.. (1970). Efficient capital markets: a review of theory and empirical work. The Journal of Finance, 25, 383-417.
Sehgal, V., & Song, C. (2007). SOPS: Stock Prediction Using Web Sentiment. Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007), 21–26.
Das, S. R. , & Chen, M. Y. . (2008). Yahoo! for amazon: sentiment extraction from small talk on the web. Operations Research, 48(6), 601-602.
Mittermayer, M. A., & Knolmayer, G. F.. (2006). NewsCATS: A News Categorization and Trading System. IEEE International Conference on Data Mining.
Lavrenko, V., Schmill, M., Lawrie, D., Ogilvie, P., Jensen, D., & Allan, J.. (2000). Language Models for Financial News Recommendation. ACM, 389-396.