Affiliation:
1. Mendel University in Brno, Czech Republic
Abstract
A lot of research has been focusing on incorporating online data into models of various phenomena. The chapter focuses on one specific problem coming from the domain of capital markets where the information contained in online environments is quite topical. The presented experiments were designed to reveal the association between online texts (from Yahoo! Finance, Facebook, and Twitter) and changes in stock prices of the corresponding companies. As the method for quantifying the association, machine learning-based classification was chosen. The experiments showed that the data preparation procedure had a substantial impact on the results. Thus, different stock price smoothing, the lags between the release of documents and related stock price changes, levels of a minimal stock price change, different weighting schemes for structured document representation, and classifiers were studied. The chapter also shows how to use currently available open source technologies to implement a system for accomplishing the task.
Reference54 articles.
1. Analyzing Financial Data and Implementing Financial Models Using R
2. Proposed efficient algorithm to filter spam using machine learning techniques. Pacific Science Review A;A. S.Aski;Natural Science and Engineering,2016
3. Pearson Correlation Coefficient
4. Text Mining
5. Price clustering and the stability of stock prices