LLM-based Stock Market Trend Prediction
Primary Area: general machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Stock Market Trend Prediction, Moving Averages, Options Volume, Market Volatility, LLM, LSTM Sentiment Analysis, Demand & Supply Dependency tree, Multi Layer Neural Networks
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: This paper explores how different factors - moving_averages, news_sentiment, options_volume, LLMs priority index could affect trends in stock market.
Abstract: LLM-based Stock Market Trend Prediction
Investor sentiment, which is driven by 'intriguing factors' such as news articles and options volume, has been historically resistant to effective use in quantitative methods for predictive market analysis. The emerging science of large language models (LLMs), however, offers a potential solution to this problem. In this paper, we describe our initial experiments with a novel system which prompts available LLMs in a way which allows us to link responses with features in the otherwise more traditional quantitative methods. The results show high accuracy in predicting market moves. We describe the experiments and our initial thoughts about next steps in the paper.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8637
Loading