Stock Price Prediction using Quotes and Financial News
Manisha V. Pinto1, Kavita Asnani2
1Manisha V. Pinto, Department of Information Technology (M.E.), Padre Conceicao College of Engineering, Goa University, Verna, India.
2Kavita Asnani, Department of Information Technology (M.E.), Padre Conceicao College of Engineering, Goa University, Verna, India.
Manuscript received on October 09, 2011. | Revised Manuscript received on October 21, 2011. | Manuscript published on November 05, 2011. | PP: 266-269 | Volume-1 Issue-5, November 2011. | Retrieval Number: E0216101511/2011©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper provides a framework for predicting stock magnitude and trend for making trading decisions by making use of a combination of Data Mining and Text Mining methods. The prediction model predicts the stock market closing price for a given trading day ‘D’, by analysing the information rich unstructured news articles along with the historical stock quotes. In particular, we investigate the immediate impact of the news articles on the time series based on Efficient Market Hypothesis (EMH). Key phrases provide semantic metadata that summarize and characterize documents. This framework incorporates Kea [1], an algorithm for automatically extracting key phrases from news articles. The prediction power of the Neural Network is used for predicting the closing price for a given trading day. The Neural Network is trained on the extracted key phrases and the stock quotes using the Back propagation Algorithm.
Keywords: Stock Market, Dow Jones Industrial Average, Key Phrase Extraction Algorithm (KEA), Neural Network, Back Propagation Algorithm.