Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting
Study on using Large Language Models for explainable financial time series forecasting, focusing on NASDAQ-100 stocks.
What it examines
This paper explores the use of Large Language Models (LLMs) for explainable financial time series forecasting, focusing on NASDAQ-100 stocks. It addresses challenges in cross-sequence reasoning, multi-modal data integration, and model interpretability using GPT-4 and Open LLaMA models.
What it concludes
The research highlights the potential of LLMs in financial forecasting, offering improved accuracy and explainability. Future work could expand to other stock indexes and data types, enhancing financial decision-making transparency.
Evidence objects
The research highlights the potential of LLMs in financial forecasting, offering improved accuracy and explainability. Future work could expand to other stock indexes and data types, enhancing financial decision-making transparency.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: This paper presents a novel study on harnessing Large Language Models' (LLMs) outstanding knowledge and reasoning abilities for explainable financial time series forecasting. The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from histo… ▽ More This paper presents a novel study on harnessing Large Language Models' (LLMs) outstanding knowledge and reasoning abilities for explainable financial time series forecasting. The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from historical news, financial knowledge graphs, etc., and the issue of interpreting and explaining the model results. In this paper, we focus on NASDAQ-100 stocks, making use of publicly accessible historical stock price data, company metadata, and historical economic/financial news. We conduct experiments to illustrate the potential of LLMs in offering a unified solution to the aforementioned challenges. Our experiments include trying zero-shot/few-shot inference with GPT-4 and instruction-based fine-tuning with a public LLM model Open LLaMA. We demonstrate our approach outperforms a few baselines, including the widely applied classic ARMA-GARCH model and a gradient-boosting tree model. Through the performance comparison results and a few examples, we find LLMs can make a well-thought decision by reasoning over information from both textual news and price time series and extracting insights, leveraging cross-sequence information, and utilizing the inherent knowledge embedded within the LLM. Additionally, we show that a publicly available LLM such as Open-LLaMA, after fine-tuning, can comprehend the instruction to generate explainable forecasts and achieve reasonable performance, albeit relatively inferior in comparison to GPT-4. △ Less
Source row: 1904 · abstract type: unknown