{"paper_id":"2403.00782","title":"Ploutos: Towards interpretable stock movement prediction with financial large language model","authors":["Hanshuang Tong","Jun Li","Ning Wu","Ming Gong","Dongmei Zhang","Qi Zhang"],"paper_date":"2024-02-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2403.00782v1","page_url":"https://thequant.space/flowcharts/ploutos-towards-interpretable-stock-movement-prediction-wit/","scores":{"empirical_rigor":8.5,"math_complexity":2,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes Ploutos, a novel financial large language model framework comprising PloutosGen for multimodal analysis and PloutosGPT for interpretable stock prediction.","quote":"We propose Ploutos, a novel financial LLM framework that consists of PloutosGen and PloutosGPT.","summary":"Recent advancements in large language models (LLMs) have opened new pathways for many domains. However, the full potential of LLMs in financial investments remains largely untapped. There are two main challenges for typical deep learning-based methods for quantitative finance. First, they struggle…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Stock movement direction is determined by comparing adjusted closing prices over two consecutive trading days.","type":"market","stated":"explicit","quote":"The direction of a stock’s movement is determined by comparing its adjusted closing prices over two consecutive trading days."},{"assumption":"Positive label requires a price increase of at least 0.55%, negative label requires a decrease of at least 0.5%.","type":"data","stated":"explicit","quote":"Samples are labeled as either positive or negative based on the percentage change in closing price, with increases of 0.55% or more labeled as positive and decreases of 0.5% or more labeled as negative"},{"assumption":"Tweets are extracted using regular expression queries based on NASDAQ ticker symbols for each day, excluding weekends and public holidays.","type":"data","stated":"explicit","quote":"Each of stock contains price data obtained from Yahoo Finance and related tweets data extracted using regular expression queries based on NASDAQ ticker symbols for each day (except for weekends and public holidays)."},{"assumption":"A rolling window of T=5 trading days is used to generate samples.","type":"data","stated":"explicit","quote":"Then a T-day (T=5) rolling window is utilized to produce data candidates along the series of trading days."},{"assumption":"Training, validation, and testing splits follow a 7:1:2 ratio over specified calendar periods.","type":"data","stated":"explicit","quote":"we split the dataset into distinct sets for training (01/01/2014 to 31/07/2015), validation (01/08/2015 to 30/09/2015), and testing (01/10/2015 to 01/01/2016) in a 7:1:2 ratio."},{"assumption":"Evaluation uses accuracy, F1 score, and Matthews Correlation Coefficient (MCC) for binary classification.","type":"statistical","stated":"explicit","quote":"We adopt accuracy, F1 score, and the Matthews correlation Coefficient (MCC, sourced from sklearn’s implementations)"}]},"datasets":{"status":"available","items":[{"name":"ACL18","provider":null,"kind":"market-prices","access":"public","period":"01/01/2014 to 01/01/2016","universe":"88 high-volume trading stocks from the S&P 500 index","quote":"... we split the dataset into distinct sets for training (01/01/2014 to 31/07/2015), validation (01/08/2015 to 30/09/2015), and testing (01/10/2015 to 01/01/2016) in a 7:1:2 ratio."},{"name":"CIKM18","provider":null,"kind":"market-prices","access":"public","period":"January 2017 to November 2017","universe":"47 stocks with sufficient tweets and price data","quote":"CIKM18 consists of 47 stocks with sufficient tweets and price data ranging from January 2017 to November 2017. Similarly, we leverage the same data processing method as ACL18 to process CIKM18 dataset"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Each of stock contains price data obtained from Yahoo Finance and related tweets data extracted using regular expression queries based on NAS-DAQ ticker symbols for each day (except for week-ends and public holidays).","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Ploutos outperforms state-of-the-art methods on both prediction accuracy and interpretability.","kind":"performance","quote":"Our experiments demonstrate the effectiveness of our framework, which outperforms the state-of-the-art method on both prediction accuracy and"},{"finding":"Dynamic token weighting improves accuracy and faithfulness, with optimal temperature at 0.5 yielding maximum performance.","kind":"predictive-accuracy","quote":"When temperature equals to 0.5, both faithfulness and accuracy reach their maximum, suggesting a synergistic rather than a mutually exclusive relationship between predictive accuracy and interpretability, which also demonstrates the effectiveness of dynamic token weighting."},{"finding":"Ploutos shows superior faithfulness and informativeness compared to other LLM-based baselines.","kind":"performance","quote":"Compared to other LLM methods, Ploutos demonstrates superior faithfulness and informativeness, which indicates that large language model can be trained through specific methods to generate informative and faithful rationales, thereby enhancing model’s interpretability."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"citations":{"cited_by_in_corpus":11,"by_independent_authors":11,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":7,"unclassified":3},"independent_papers":[{"paper":{"paper_id":"2510.15691","title":"Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction","paper_date":"2025-10-17","authors":["Tian Guo","Emmanuel Hauptmann"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/exploring-the-synergy-of-quantitative-factors-and-newsflow-r/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:14:35Z"},"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/"}