mlsanityData to 14 Oct 2026

Financial Fine-tuning a Large Time Series Model

arXiv 2412.09880 ↗First posted 13 Dec 2024q-fin.CP cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Large models have shown unprecedented capabilities in natural language processing, image generation, and most recently, time series forecasting. This leads us to ask the question: treating market prices as a time series, can large models be used to predict the market? In this paper, we answer this by evaluating the performance of the latest time series foundation model TimesFM on price prediction. We find that due to the irregular nature of price data, directly applying TimesFM gives unsatisfactory results and propose to fine-tune TimeFM on financial data for the task of price prediction. This is done by continual pre-training of the latest time series foundation model TimesFM on price data containing 100 million time points, spanning a range of financial instruments spanning hourly and daily granularities. The fine-tuned model demonstrates higher price prediction accuracy than the baseline model. We conduct mock trading for our model in various financial markets and show that it outperforms various benchmarks in terms of returns, sharpe ratio, max drawdown and trading cost.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 13 Dec 2024.

Builds on

30 of 40 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  9. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  10. 2024Mixtral of Expertscited by 1,823
  11. 2021ViViT: A Video Vision Transformercited by 1,620
  12. 2016Understanding intermediate layers using linear classifier probescited by 1,353
18 more
  1. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  2. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  3. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  4. 2023A decoder-only foundation model for time-series forecastingcited by 692
  5. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  6. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 327
  7. 2021Monash Time Series Forecasting Archivecited by 267
  8. 2023FinGPT: Open-Source Financial Large Language Modelscited by 253
  9. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 169
  10. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  11. 2023TimeGPT-1cited by 158
  12. 2024Large Language Models for Time Series: A Surveycited by 114
  13. 2021Darts: User-Friendly Modern Machine Learning for Time Seriescited by 91
  14. 2019Macro F1 and Macro F1cited by 70
  15. 2024LLM Processes: Numerical Predictive Distributions Conditioned on Natural Languagecited by 55
  16. 2020On Model Evaluation under Non-constant Class Imbalancecited by 8
  17. 2021Stock Market Trend Analysis Using Hidden Markov Model and Long Short Term Memorycited by 1
  18. 2023Hidden Markov Models for Stock Market Predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Benchmarking Pre-Trained Time Series Models for Electricity Price Forecastingcited by 5
  2. 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challengescited by 4
  3. 2025CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streamscited by 4
  4. 2026Post-Training in Time Series Foundation Models: A Unifying Frameworkcited by 3
  5. 2025Estimating Time Series Foundation Model Transferability via In-Context Learningcited by 2
  6. 2026Unified Zero-Shot Time Series Forecasting: A Darts Foundationcited by 0
  7. 2026When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecastingcited by 0
  8. 2026SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Modelscited by 0