{"paper_id":"2409.08281","title":"StockTime: A Time Series Specialized Large Language Model Architecture for Stock Price Prediction","authors":["Shengkun Wang","Taoran Ji","Linhan Wang","Yanshen Sun","Shang-Ching Liu","Amit Kumar","Chang-Tien Lu"],"paper_date":"2024-08-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.08281v1","page_url":"https://thequant.space/flowcharts/stocktime-a-time-series-specialized-large-language-model-ar/","scores":{"empirical_rigor":4,"math_complexity":7.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes StockTime, an LLM-based architecture that treats stock prices as tokens and extracts textual information from them for price prediction.","quote":"We introduce StockTime, a novel LLM-based architecture designed specifically for stock price data.","summary":"The stock price prediction task holds a significant role in the financial domain and has been studied for a long time. Recently, large language models (LLMs) have brought new ways to improve these predictions. While recent financial large language models (FinLLMs) have shown considerable progress…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The model can rely solely on adjusted close price without any external textual data.","type":"data","stated":"implied","quote":"For Stocktime, we only used the adjusted close price for experiments."},{"assumption":"Freezing the pre‑trained LLM and training only embedding and projection layers is sufficient for good performance.","type":"model","stated":"implied","quote":"and projection layers of the stock time series, we significantly reduce training costs."},{"assumption":"Stock price movements can be modeled as next‑token prediction in an autoregressive fashion.","type":"model","stated":"explicit","quote":"It leverages the natural ability of LLMs to predict the next token by treating stock prices as consecutive tokens"},{"assumption":"Historical price data from Yahoo Finance for S&P 100 constituents is representative of the market.","type":"market","stated":"implied","quote":"We sourced historical stock price data for S&P 100 companies from Yahoo Finance2 for the period from June 30, 2014, to June 28, 2024."},{"assumption":"The look‑back window can be selected from {16,32,64,128,256} without loss of generality.","type":"model","stated":"implied","quote":"The lookback window is choosen from {16,32,64,128,256}"}]},"datasets":{"status":"available","items":[{"name":"S&P 100 historical prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2014-06-30 to 2024-06-28","universe":"S&P 100 constituents","quote":"We sourced historical stock price data for S&P 100 companies from Yahoo Finance2 for the period from June 30, 2014, to June 28, 2024.","known_id":"yahoo-finance"},{"name":"S&P 100 hourly medium‑frequency dataset","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2023-06-30 09:30 to 2024-07-16 15:30","universe":"S&P 100 constituents","quote":"We also created a hourly medium-frequency stock dataset using companies from the S&P 100, covering the period from June 30, 2023, 9:30 to July 16, 2024, 15:30.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"To ensure the datasets accurately repre-sent the stock market, we sourced historical stock price data for S&P 100 companies from Yahoo Finance2 for the period from June 30, 2014, to June 28, 2024.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"StockTime outperforms both general LLMs and FinLLMs on all tested datasets, achieving up to a 5% improvement in stock price movement prediction.","kind":"performance","quote":"Compared to FinLLM, our framework outperformed them on most datasets containing textual data, achieving up to a 5% improvement in stock price movement prediction."},{"finding":"Ablation shows that removing the autoregressive encoder or the textual information degrades performance, confirming the importance of both components.","kind":"performance","quote":"When the textual information was removed, StockTime’s performance slightly declined, underscoring the importance of integrating multimodal data."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"citations":{"cited_by_in_corpus":4,"by_independent_authors":4,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":4,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T16:36:11Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}