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.

本文研究了利用大型语言模型在可解释金融时间序列预测中的应用，使用股票价格数据、公司元数据和历史新闻等多模态信号，在 NASDAQ-100 股票上进行实验，结果显示与一些基准模型相比，使用 GPT-4 和 Open LLaMA 这类新型模型进行零样本 / 少样本推断并通过基于指令的微调生成可解释预测，优于经典的 ARMA-GARCH 模型和梯度提升树模型。

时间序列数据与 LLM 相遇 - 可解释的金融时间序列预测

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

Forecasting financial time series has long been a challenging problem that
has attracted attention from both researchers and practitioners. Statistical
and machine learning techniques have both been explored to develop effective
forecasting models in the past few decades. With recent developments in deep
learning models, financial time series forecasting models have advanced
significantly, and these developments are often difficult to keep up with.
Hence, we have conducted this literature review to provide a comprehensive
assessment of recent research from 2020 to 2022 on deep learning models used to
predict prices based on financial time series. Our review presents different
data sources and neural network structures, as well as their implementation
details. Our goals are to ensure that interested researchers remain up-to-date
on recent developments in the field and facilitate the selection of baselines
based on models used in prior studies. Additionally, we provide suggestions for
future research based on the content in this review.

本文综述了近年来 2020 至 2022 年关于利用深度学习模型基于金融时序数据预测价格的研究，包括不同数据源和神经网络结构的实现细节，旨在让研究人员了解该领域最新进展，方便选择先前研究中使用的模型基线，并提供未来研究建议。

2020-2022 年间金融时序预测的深度学习技术进展综述

Deep learning techniques for financial time series forecasting: A review  of recent advancements: 2020-2022

We present a method for conditional time series forecasting based on an
adaptation of the recent deep convolutional WaveNet architecture. The proposed
network contains stacks of dilated convolutions that allow it to access a broad
range of history when forecasting, a ReLU activation function and conditioning
is performed by applying multiple convolutional filters in parallel to separate
time series which allows for the fast processing of data and the exploitation
of the correlation structure between the multivariate time series. We test and
analyze the performance of the convolutional network both unconditionally as
well as conditionally for financial time series forecasting using the S&P500,
the volatility index, the CBOE interest rate and several exchange rates and
extensively compare it to the performance of the well-known autoregressive
model and a long-short term memory network. We show that a convolutional
network is well-suited for regression-type problems and is able to effectively
learn dependencies in and between the series without the need for long
historical time series, is a time-efficient and easy to implement alternative
to recurrent-type networks and tends to outperform linear and recurrent models.

本文提出了一种基于改进的深度卷积 WaveNet 框架的条件时间序列预测方法，该方法通过多个卷积滤波器并行应用于各个时间序列来完成条件操作，从而加速数据处理和利用多元时间序列之间的相关性，可以有效地学习和预测金融时间序列，且性能优于常用的自回归模型和长短期记忆网络。