{"paper_id":"2411.08899","title":"FinVision: A Multi-Agent Framework for Stock Market Prediction","authors":["Sorouralsadat Fatemi","Yuheng Hu"],"paper_date":"2024-10-29","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2411.08899v1","page_url":"https://thequant.space/flowcharts/finvision-a-multi-agent-framework-for-stock-market-predicti/","scores":{"empirical_rigor":5,"math_complexity":1.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a multi-modal multi-agent framework, FinVision, for financial trading tasks.","quote":"This research introduces a multi-modal multi-agent system designed specifically for financial trading tasks.","summary":"Financial trading has been a challenging task, as it requires the integration of vast amounts of data from various modalities. Traditional deep learning and reinforcement learning methods require large training data and often involve encoding various data types into numerical formats for model…","strategy":"FinVision multi-agent trading framework"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance news articles","provider":"Yahoo Finance","kind":"text-news","access":"public","period":"April 1, 2023 to December 29, 2023","universe":"Apple (AAPL), Amazon (AMZN), Microsoft (MSFT)","quote":"daily candlestick charts, technical indicators, and reflection data.","known_id":"yahoo-finance"},{"name":"Daily candlestick charts and technical indicators","provider":null,"kind":"market-prices","access":"public","period":"April 1, 2023 to December 29, 2023","universe":"Apple (AAPL), Amazon (AMZN), Microsoft (MSFT)","quote":"The candlestick charts, technical indicators, and trading signal images for reflection were all plotted using Matplotlib and various finance libraries."}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The dataset comprises news articles sourced from Yahoo Finance,2 daily candlestick charts, technical indicators, and reflection data.","mentions":1,"used_in":1}],"sample":{"start":"2023-06","end":"2023-12","market":"technology stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"FinVision achieved a 14.79% ARR and a Sharpe Ratio of 1.20 for AAPL, outperforming the market buy‑and‑hold ARR of 13.56% and Sharpe 0.67.","kind":"performance","quote":"For AAPL, the framework achieved a 14.79% ARR and a Sharpe Ratio of 1.20, compared to the market’s 13.56% ARR and 0.67 Sharpe Ratio."},{"finding":"For MSFT, FinVision recorded a 25.57% ARR and Sharpe Ratio of 1.41, surpassing the market’s 22.27% ARR and Sharpe 1.01.","kind":"performance","quote":"Similarly, for MSFT, our framework’s ARR of 25.57% and Sharpe Ratio of 1.41 surpassed the market’s 22.27% ARR and 1.01 Sharpe Ratio."},{"finding":"FinVision’s ARR for AMZN was 42.14% with a Sharpe Ratio of 1.72, lower ARR than market (43.57%) but higher Sharpe and lower max drawdown (12.09% vs 17.45%).","kind":"performance","quote":"Although the framework’s 42.14% ARR for AMZN slightly lagged behind the market’s 43.57% ARR, it significantly improved risk‑adjusted performance, achieving a Sharpe Ratio of 1.72 (compared to the market’s 1.37) and a lower Maximum Drawdown of 12.09% (versus 17.45% for the market)."},{"finding":"FinVision outperformed RL‑based models: for AAPL, PPO achieved 7.26% ARR and -0.42 Sharpe, DQN 1.22% ARR and -0.90 Sharpe, while FinVision had 14.79% ARR and 1.20 Sharpe.","kind":"performance","quote":"For instance, with AAPL, our framework’s 14.79% ARR and 1.20 Sharpe Ratio far exceeded those of PPO (7.26% ARR, -0.42 Sharpe Ratio) and DQN (1.22% ARR, -0.90 Sharpe Ratio)."},{"finding":"FinVision underperformed compared to the FinAgent model, which used extensive training data, though it required much less training time.","kind":"negative","quote":"However, our method underperformed compared to the FinAgent model, which underscores the efficiency of their extensive training data."}],"reported_performance":{"strategy":"FinVision multi-agent trading framework","sharpe":1.72,"sharpe_benchmark":1.37,"annual_return_pct":42.14,"total_return_pct":null,"max_drawdown_pct":12.09},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"citations":{"cited_by_in_corpus":7,"by_independent_authors":7,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":1,"discusses_findings":0,"mentions":3,"unclassified":3},"independent_papers":[{"paper":{"paper_id":"2510.17393","title":"3S-Trader: A Multi-LLM Framework for Adaptive Stock Scoring, Strategy, and Selection in Portfolio Optimization","paper_date":"2025-10-20","authors":["Kefan Chen","Hussain Ahmad","Diksha Goel","Claudia Szabo"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/3s-trader-a-multi-llm-framework-for-adaptive-stock-scoring/"},"how":"extends","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":"2026-11-14T17:57:09Z"},"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/"}