Stock Trading Using a Deep Reinforcement Learning and Text Analysis
|Author:||Bc. Dominik Benk|
|Year:||2022 - summer|
|Leaders:|| doc. PhDr. Jozef Baruník Ph.D.
|Work type:|| Finance, Financial Markets and Banking
|Awards and prizes:||Deloitte Outstanding Thesis Award.|
|Abstract:||The thesis focuses on exploiting imperfections on the stock market by utilizing
state-of-the-art learning methods and applying them to algorithmic trading.
The automated decisions are expected to have the capability of outperforming
professional traders by considering much more information, reacting almost
instantly and being unaffected by emotions. As an alternative to traditional
supervised learning, the proposed model of reinforcement learning employs a
principle of trial-and-error, which is essential for learning behaviours of all
organisms. In the context of stocks, this allows to consider the involved uncertainty and therefore more precisely estimate the long-run returns. To collect
the most relevant information for each trading decision, additionally to technical indicators the models build on investor’s opinion - financial sentiment.
This is derived from two textual sources, news and social media, and the main
goal is to compare their relative contribution to trading. Models are applied to
11 different stocks and later combined into portfolio for greater robustness of
results. The textual analysis proves to be important for the learning process,
especially in case of stocks with good media coverage. The Twitter is found to
provide more valuable information compared to news, but their combination
shows even higher predictive potential. Nevertheless, proposed models have
difficulties to reliably outperform passive strategies or the market.