Quantitative Day Trading from Natural Language using Reinforcement Learning

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4018–4030 June 6–11, 2021. ©2021 Association for Computational Linguistics 4018 Quantitative Day Trading from Natural Language using Reinforcement Learning Ramit Sawhney* IIIT Delhi ramits@iiitd.ac.in Arnav Wadhwa* MIDAS, IIIT Delhi arnavw96@gmail.com Shivam Agarwal Manipal Institute of Technology shivamag99@gmail.com Rajiv Ratn Shah IIIT Delhi rajivratn@iiitd.ac.in Abstract It is challenging to design profitable and prac- tical trading strategies, as stock price move- ments are highly stochastic, and the market is heavily influenced by chaotic data across sources like news and social media. Existing NLP approaches largely treat stock prediction as a classification or regression problem and are not optimized to make profitable invest- ment decisions. Further, they do not model the temporal dynamics of large volumes of di- versely influential text to which the market re- sponds quickly. Building on these shortcom- ings, we propose a deep reinforcement learn- ing approach that makes time-aware decisions to trade stocks while optimizing profit using textual data. Our method outperforms state-of- the-art in terms of risk-adjusted returns in trad- ing simulations on two benchmarks: Tweets (English) and financial news (Chinese) pertain- ing to two major indexes and four global stock markets. Through extensive experiments and studies, we build the case for our method as a tool for quantitative trading. 1 Introduction The stock market, a financial ecosystem involv- ing quantitative trading and investing, observed a market capitalization exceeding $US 60 trillion as of the year 2019. Stock trading presents lucra- tive opportunities for investors to utilize the market as a platform for investing funds and maximizing profits. However, making profitable investment de- cisions is challenging due to the market’s volatile, noisy, and chaotic nature (Tsay, 2005; Adam et al., 2016). Research at the intersection of Natural Language Processing (NLP) and finance presents encouraging prospects in stock prediction (Jiang, 2020). Conventional work forecasts future trends by modeling numerical historical stock data (Lu *Equal contribution. Figure 1: Here, we show how tweets about Tesla and Moderna influence investors’ opinions and impact the stocks over a day and the upcoming week. The tweets by the Tesla CEO Elon Musk lead to massive price drops in Tesla’s stock, and Moderna’s positive news at- tracts investments in its stock. A profitable trading de- cision would entail selling off Tesla’s shares (if already held) and buying Moderna’s stock in such a scenario. et al., 2009; Bao et al., 2017). However, price sig- nals alone can not capture market surprises, merg- ers, acquisitions, and company announcements. Such events, often reported across financial news and social media, have strong influence over market dynamics (Laakkonen, 2004). For instance, prices immediately react to breaking news about the re- lated company (Busse and Green, 2002). Such reactions conform to the Efficient Market Hypoth- esis (EMH), a hypothesis in finance which states that financial markets are informationally efficient and prices reflect all available market information at any given time (Malkiel, 1989). The abundance of stock affecting information across …

Content truncated to 500 words