This thesis investigates how the CEO’s comments in quarterly reports affect the financial performance of a company by predicting their stock price using machine learning and natural language processing. The dataset used consists of historical information such as the stock price (quantitative data) and the CEO’s comments (qualitative data). Where the qualitative information was embedded using the paragraph vector document embedding technique and used with the quantitative data in three type of models. The models tested was Support Vector Machine and Artificial Neural Network against a Naive Bayes base- line. Further, each model was trained and evaluated using the quantitative, qualitative and both datasets and the results were confirmed using statistical significant testing. Finally, the best models from the evaluation step were used to simulate a trading strategy to buy the stock if the model predicted that the price of the stock would rise. The statistically significant improvements of using the CEO’s comments and the hypothetical profits the trading strategies rendered show that the CEO’s comments adds some predictive ability in terms of their stock price and thus their financial performance.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-166361 |
Date | January 2020 |
Creators | Westerdahl, Ludvig |
Publisher | Linköpings universitet, Institutionen för datavetenskap |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.002 seconds