Abstract:
|
Predicting the financial performance of companies using various data sources has been the focus of a large number of studies. However, current models can still be improved. This research makes multiple contributions to knowledge. First, this research introduces a new method to more accurately predict the probability that a company’s credit rating changes. More specifically, this research exploits the vast increase in social media data put out by companies, that enables one to develop more predictive models than those developed in the past. By analysing the tweets put out by different companies, we show that there is a correlation between specific words in the tweets and the credit rating. Furthermore, we will show that using these words in a predictive model leads to an increase in predictive power when comparing with a model not containing these words as predictors. For identifying linguistic features in tweets that are most predictive of a change in credit ratings, Differential Language Analysis is used, a method that has not been used in a financial context before. Another contribution is the used big dataset, containing twitter data as well as data on the companies.
|