{"paper_id":"2412.09394","title":"LLMs for Time Series: an Application for Single Stocks and Statistical Arbitrage","authors":["Sebastien Valeyre","Sofiane Aboura"],"paper_date":"2024-12-12","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.09394v2","page_url":"https://thequant.space/flowcharts/llms-for-time-series-an-application-for-single-stocks-and-s/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using the Chronos large language model, both pretrained and fine‑tuned, to forecast residual returns of large US single stocks and build a long/short portfolio.","quote":"Specifically, we utilized the Chronos model from Ansari et al.(2024) and tested both pretrained configurations and fine‑tuned supervised forecasts on the largest American single stocks using data from Guijarro‑Ordonnez et al.(2022).","summary":"Recently, LLMs (Large Language Models) have been adapted for time series prediction with significant success in pattern recognition. However, the common belief is that these models are not suitable for predicting financial market returns, which are known to be almost random. We aim to challenge…","strategy":"Chronos (LLM) with resized fine‑tuned weights"},"assumptions":{"status":"available","items":[{"assumption":"The performance metric ignores slippage and trading costs.","type":"execution","stated":"explicit","quote":"We based our results on the gross Sharpe ratio metric of the portfolio which corresponds to the outsample annualized average of daily returns of the portfolio divided by the annualized standard deviation of daily returns, meaning that we do not consider slippage and trading costs."},{"assumption":"Only large, liquid stocks (e.g., S&P 500 constituents) are used to ensure robustness.","type":"market","stated":"explicit","quote":"Their methodology underscores the importance of focusing on larger, more liquid stocks, such as those in the S&P 500, to ensure robustness in empirical findings."},{"assumption":"Residual returns are less correlated and thus suitable for deep learning.","type":"data","stated":"explicit","quote":"Using residual returns allows for a less correlated dataset, which is crucial for deep learning."},{"assumption":"The zero‑shot Chronos model can be applied without a larger dataset because it is pretrained on non‑financial data.","type":"model","stated":"explicit","quote":"Also as we mainly use the pretrained case of Chronos, we did not need a larger dataset for the zeros shot version or the fine tuned one."},{"assumption":"A 3 basis‑point per‑trade cost approximates typical market impact and brokerage fees.","type":"execution","stated":"explicit","quote":"A transaction cost of 3 basis points per trade is consistent with the average market impact—typically between 2 and 3 basis points for very small orders—and brokerage fees of approximately 1 basis point."}]},"datasets":{"status":"available","items":[{"name":"IPCA residual returns","provider":"Guijarro‑Ordonnez et al. (2021) – GitHub","kind":"market-prices","access":"public","period":"January 1978 to end of 2016","universe":"CRSP securities universe","quote":"The three different datasets of daily residual returns (IPCA, PCA and FF) provided by Guijarro‑Ordonnez et al. (2021) are all based on the same raw universe of securities from the CRSP dataset spanning January 1978 to the end of 2016."},{"name":"PCA residual returns","provider":"Guijarro‑Ordonnez et al. (2021) – GitHub","kind":"market-prices","access":"public","period":"January 1978 to end of 2016","universe":"CRSP securities universe","quote":"The three different datasets of daily residual returns (IPCA, PCA and FF) provided by Guijarro‑Ordonnez et al. (2021) are all based on the same raw universe of securities from the CRSP dataset spanning January 1978 to the end of 2016."},{"name":"FF residual returns","provider":"Guijarro‑Ordonnez et al. (2021) – GitHub","kind":"market-prices","access":"public","period":"January 1978 to end of 2016","universe":"CRSP securities universe","quote":"The three different datasets of daily residual returns (IPCA, PCA and FF) provided by Guijarro‑Ordonnez et al. (2021) are all based on the same raw universe of securities from the CRSP dataset spanning January 1978 to the end of 2016."}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"The three different datasets of daily residual returns (IPCA, PCA and FF) provided by Guijarro-Ordonnez et al. (2021) are all based on the same raw universe of securities from the CRSP dataset spanning January 1978 to the end of 2016, but obtained using different methods for extracting the residuals.","mentions":1,"used_in":1}],"sample":{"start":"2002","end":"2016","market":"US single stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"A flat 3 basis‑point slippage cost per trade is applied in a robustness check, turning positive gross Sharpe ratios into negative net Sharpe ratios.","quote":"trading costs are prohibitive, as including a 3 basis point slippage","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"A flat 3 basis‑point slippage cost per trade is applied in a robustness check, turning positive gross Sharpe ratios into negative net Sharpe ratios.","card_quote":"trading costs are prohibitive, as including a 3 basis point slippage","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The pretrained Chronos model with α = 0.3 achieves a gross Sharpe ratio above 3.17 for the PCA dataset over a 15‑year period.","kind":"performance","quote":"We observe that the pre‑trained Chronos model with the autoregressive coefficient α = 0.3 effectively identifies opportunities in the financial market (see Table 2), achieving a Sharpe ratio above 3.17 for PCA over a 15‑year period, which corresponds to a t‑statistic of 3.17 √15 = 12.27."},{"finding":"When a 3‑basis‑point transaction cost is applied, the net Sharpe ratio for PCA drops from 3.17 to –1.49.","kind":"negative","quote":"With α = 0.3, the gross Sharpe ratio for PCA is 3.17, but it drops to -1.49 after accounting for a 3 basis point trading cost."},{"finding":"Chronos becomes highly correlated with the Short‑Term Reversal (STR) strategy (β = 0.3) but does not outperform it.","kind":"performance","quote":"However, it ultimately gets very correlated to the Short‑Term Reverseal (STR) strategy with β = 0.3 but fails to outperform it."},{"finding":"The STR strategy outperforms AutoARIMA, showing higher Sharpe ratios across factor datasets.","kind":"performance","quote":"That assertion is supported by the case of the strong outperformance of the STR compared to AutoARIMA, which can capture more complexity but whose noisy fit makes it suboptimal and overly erratic."}],"reported_performance":{"strategy":"Chronos (LLM) with resized fine‑tuned weights","sharpe":4.21,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/dkyol/Asset-Pricing-Model","note":null},"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":"2026-11-14T17:50:14Z"},"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/"}