Reasoning on Time-Series for Financial Technical Analysis
Kelvin J.L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua
虽然大型语言模型已被用于生成可解释的股票预测,但它们主要集中在分析文本报告而不是历史价格数据,也称为技术分析。 这项任务具有挑战性,因为它在域之间切换:股价输入和输出位于时间序列域中,而推理步骤应该是自然语言。 在这项工作中,我们引入了口头技术分析(VTA),这是一个新颖的框架,结合了口头和潜在推理,可以产生既准确又可解释的股票时间序列预测。 为了推理时间序列,我们将股价数据转换为文本注释,并使用反向平均方块误差(MSE)奖励目标优化推理跟踪。 为了从文本推理中产生时间序列输出,我们将时间序列主干模型的输出与基于推理的属性进行调节。 美国、中国和欧洲市场对股票数据集的实验表明,VTA实现了最先进的预测准确性,而推理痕迹在行业专家的评估中也表现良好。
While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to pr...