Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. Existing approaches typically employ an autoregressive generation strategy to adapt LLMs for TSF. However, we identify a theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, recursively consuming its own generated outputs. This leads to error accumulation, where minor early deviations cascade into significant rollout drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing Feedback-driven LLM (F-LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator functioning as a system observer. Furthermore, we provide a mathematical proof that, under explicit contraction assumptions, this closed-loop mechanism guarantees a uniformly bounded step-wise error sequence within the local surrogate dynamics. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks. Our code is publicly available at https://github.com/Zh-XY22/F-LLM.
我们采用随机森林和LSTM网络(更准确地说是CuDNNLSTM)作为训练方法,分析它们在预测1993年1月至2018年12月期间标准普尔500指数成分股的样本外方向性走势方面的有效性。我们引入了一个多功能的设置,不仅包括收盘价的回报,但也相对于开盘价和日内回报。作为交易策略,我们使用Krauss et al.(2017)和Fischer & Krauss(2018)作为基准。在每个交易日,我们买入概率最高的10只股票,卖空概率最低的10只股票,以获得超过市场的日内回报--所有股票的货币权重都是相同的。我们的实证结果表明,在交易成本之前,多特征设置使用LSTM网络提供了0.64%的每日回报,使用随机森林提供了0.54%的每日回报。因此,我们的表现优于Fischer & Krauss(2018)和Krauss et al.(2017)中的单一特征设置,仅包括收盘价的每日回报,LSTM和随机森林的相应每日回报分别为0.41%和0.39%。
Cryptocurrency Price Forecasting Using XGBoost Regressor and Technical Indicators
ESISA Analytica, Higher School of Engineering in Applied Sciences(ESISA分析与应用科学高等工程学院);GAIA, Ericsson(GAIA、爱立信);Fordham University(福特汉姆大学);Penn State University(宾夕法尼亚州立大学)
A Machine Learning Approach For Bitcoin Forecasting
institutetext: 1 Universidad Privada Boliviana, Computational Systems Engineering, Cochabamba, Bolivia 2 University of Warsaw, Faculty of Economic Sciences, Poland(玻利维亚私人大学、经济科学学院,波兰华沙大学)
Xiaohongshu Inc.(小红书公司);College of Control Science and Technology, Zhejiang University(浙江大学控制科学与工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics(上海财经大学计算与人工智能学院);State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室);Squirrel AI(松鼠AI);Center for Data Science, Peking University(北京大学数据科学中心);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting
Mechanical Engineering and Applied Mechanics, University of Pennsylvania(宾夕法尼亚大学机械工程与应用力学系);Department of Mathematics, Tufts University(塔夫茨大学数学系);Department of Mathematics and Cybernetics, SINTEF Digital(SINTEF数字技术部门数学与控制系);Department of Mathematical Sciences, Norwegian University of Science and Technology(挪威科技大学数学科学系);Department of Physics, University of Oslo(奥斯陆大学物理系);Sandia National Laboratories(桑地亚国家实验室)
FreqLens: Interpretable Frequency Attribution for Time Series Forecasting
Independent Researcher(独立研究者);Indiana University at Bloomington(印第安纳大学布卢明顿分校);National Yang Ming Chiao Tung University;National Taiwan University(国立台湾大学);Boise State University(博伊州立大学)
Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
Tsinghua University(清华大学);University of Science and Technology of China(中国科学技术大学);The Chinese University of Hong Kong(香港中文大学);Nanyang Technological University(南洋理工大学);Tencent(腾讯)
HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
Civil, Environmental, and Architectural Engineering, University of Colorado Boulder(科罗拉多大学波尔德分校土木、环境与建筑工程系);Civil Engineering and Environmental Sciences, University of Oklahoma(俄克拉荷马大学土木工程与环境科学系);Department of Computer Science, University of Oklahoma(俄克拉荷马大学计算机科学系);Civil and Environmental Engineering, Stanford University(斯坦福大学土木与环境工程系);Department of Computer Science, Stanford University(斯坦福大学计算机科学系);NASA Goddard Space Flight Center(美国国家航空航天局戈达德空间飞行中心)
Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting
Griffith University(格里菲斯大学);Monash University(莫纳什大学);University of Stuttgart(斯图加特大学);Alibaba Group(阿里巴巴集团);University of New South Wales(新南威尔士大学);Emory University(埃默里大学);Squirrel Ai Learning