PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting

• URL: http://arxiv.org/abs/2609.05235v1
• Date: Fri, 04 Sep 2026 15:01:38 GMT
• Title: PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
• Abstract summary: This study introduces PRICE, a structured approach for adapting Large Language Models to short-term Bitcoin price forecasting.<n>Built on a 4-bit quantized LLaMA-3 8B model, PRICE investigates how fine-tuning, numerical representation, prompting, inference, and decoding jointly influence performance.<n>Price achieves the lowest forecasting errors on both validation and test sets while maintaining robust performance across evaluation periods.
• Score: 0.40105987447353786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language Models (LLMs) have shown promise for time series forecasting, the combined effects of adaptation choices remain largely unexplored in financial settings. This study introduces PRICE, a structured approach for adapting LLMs to short-term Bitcoin price forecasting. Built on a 4-bit quantized LLaMA-3 8B model, PRICE investigates how fine-tuning, numerical representation, prompting, inference, and decoding jointly influence forecasting performance. PRICE integrates Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA), Recursive multi-step inference, Integer-rounded numerical representation, Context-Task-Format (CTF) prompting, and Exact zero-temperature decoding. Ablation studies show that each component contributes to forecasting accuracy and reliability. LoRA enables efficient training on limited hardware, recursive inference improves accuracy, integer-rounded values reduce errors, CTF prompting outperforms Chain-of-Thought, Implicit Chain-of-Thought (iCoT), and few-shot prompting, and zero-temperature decoding improves stability during recursive forecasting. Comparative evaluation against eight transformer-based and time-series foundation models shows that PRICE achieves the lowest forecasting errors on both validation and test sets while maintaining robust performance across evaluation periods. Despite being based on a model primarily pretrained on text rather than time-series data, PRICE achieves competitive or superior performance relative to specialized foundation models. These findings demonstrate that adaptation choices critically determine the accuracy and robustness of LLMs for numerical time-series forecasting.

Related papers

• Efficient Test-Time Scaling for LLM-based Time Series Forecasting [21.66751156586705]
  Long-term time series forecasting benefits from preserving global structure such as trends and seasonality.<n>Recent LLM-based forecasters often improve accuracy through test-time scaling.<n>But these methods are computationally expensive and prone to global-shape mismatch as the prediction horizon extends.<n>We propose a lightweight Transformer tailored to long-term shape modeling to predict a coarse representation of future dynamics.
  arXiv  Detail & Related papers  (2026-08-09T12:45:08Z)
• Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs [34.87727677131385]
  We introduce StockR1, a time-series-enhanced LLM that unifies stock forecasting and financial reasoning through a verifiable forecast action.<n>Based on a tool-call design, the model first emits a forecast action, which is a structured and interpretable representation of its qualitative market outlook.<n>We optimize the full pipeline with reinforcement learning, where rewards jointly reflect answer validity, forecast accuracy, and consistency between generated actions and observed time-series dynamics.
  arXiv  Detail & Related papers  (2026-05-21T04:09:16Z)
• Nexus : An Agentic Framework for Time Series Forecasting [72.73790673303154]
  Time series forecasting requires reasoning with unstructured contextual data such as news or events.<n>We introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages.<n>We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized.
  arXiv  Detail & Related papers  (2026-05-14T05:12:13Z)
• Convolutionally Low-Rank Models with Modified Quantile Regression for Interval Time Series Forecasting [18.452655953569696]
  Interval time series forecasting offers a principled solution to the problem of quantifying uncertainty.<n>We consider a recently established point forecasts (PFs) method termed Learning-Based Convolution Nuclear Norm Minimization (LbCNNM)<n>While theoretically complete and empirically effective, LbCNNM lacks inherent uncertainty estimation capabilities.<n>We modify the well-known Quantile Regression (QR) and integrate it into LbCNNM, resulting in a novel interval forecasting method termed LbCNNM with Modified Quantile Regression (LbCNNM-MQR)
  arXiv  Detail & Related papers  (2026-04-17T07:52:21Z)
• TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems [52.91956121737963]
  We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems.<n>We propose a systematic multi-agent framework that utilizes an iterative verification loop to synthesize numerically grounded reasoning traces.<n>Our evaluation confirms that this reasoning is causally effective; useful for evaluation; and prompting LLMs with our generated traces significantly improves forecasting accuracy.
  arXiv  Detail & Related papers  (2026-04-07T03:04:45Z)
• ZIP-RC: Optimizing Test-Time Compute via Zero-Overhead Joint Reward-Cost Prediction [57.799425838564]
  We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost.<n> ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost.
  arXiv  Detail & Related papers  (2025-12-01T09:44:31Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model [27.20045729222667]
  FinZero is a multimodal pre-trained model finetuned by UARPO to perform reasoning, prediction, and analytical understanding on the FVLDB financial time series.<n>After fine-tuning with UARPO, FinZero achieves an approximate 13.48% improvement in prediction accuracy over GPT-4o in the high-confidence group.
  arXiv  Detail & Related papers  (2025-09-10T16:32:41Z)
• BreakGPT: Leveraging Large Language Models for Predicting Asset Price Surges [55.2480439325792]
  This paper introduces BreakGPT, a novel large language model (LLM) architecture adapted specifically for time series forecasting and the prediction of sharp upward movements in asset prices. We showcase BreakGPT as a promising solution for financial forecasting with minimal training and as a strong competitor for capturing both local and global temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-09T05:40:32Z)
• Feature Selection with Annealing for Forecasting Financial Time Series [2.44755919161855]
  This study provides a comprehensive method for forecasting financial time series based on tactical input output feature mapping techniques using machine learning (ML) models. Experiments indicate that the FSA algorithm increased the performance of ML models, regardless of problem type.
  arXiv  Detail & Related papers  (2023-03-03T21:33:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.