{"paper_id":"2502.00828","title":"Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization","authors":["Yoontae Hwang","Yaxuan Kong","Stefan Zohren","Yongjae Lee"],"paper_date":"2025-02-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.00828v1","page_url":"https://thequant.space/flowcharts/decision-informed-neural-networks-with-large-language-model/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a decision-informed neural network framework that integrates large language models for portfolio optimization, using attention mechanisms and a hybrid loss.","quote":"We develop a decision-informed neural network framework that integrates LLMs for portfolio optimization.","summary":"This paper addresses the critical disconnect between prediction and decision quality in portfolio optimization by integrating Large Language Models (LLMs) with decision-focused learning. We demonstrate both theoretically and empirically that minimizing the prediction error alone leads to suboptimal…","strategy":"Decision-Informed Neural Network (DINN)"},"assumptions":{"status":"available","items":[{"assumption":"Only companies that maintained consistent index membership throughout the study period are included to avoid survivorship bias.","type":"data","stated":"explicit","quote":"To address potential survivorship bias, we include only companies that maintained consistent index membership throughout the study period."},{"assumption":"Macroeconomic indicators from FRED are predictive of asset returns.","type":"market","stated":"implied","quote":"selected based on their documented predictive power in asset pricing: weekly initial jobless claims (ICSA), consumer sentiment (UMCSENT), new home sales (HSN1F), unemployment rate (UNRATE), and high-yield bond spread (HYBS)."}]},"datasets":{"status":"available","items":[{"name":"DOW 30 equity returns","provider":"WRDS","kind":"market-prices","access":"commercial","period":"January 2010 to December 2023","universe":"DOW 30 constituents","quote":"Our primary data consists of equity returns from two major indices: the DOW 30 and a market-cap-weighted subset of 50 constituents from the S&P 100.","known_id":"wrds"},{"name":"S&P 100 subset equity returns","provider":"WRDS","kind":"market-prices","access":"commercial","period":"January 2010 to December 2023","universe":"50 constituents from the S&P 100","quote":"Our primary data consists of equity returns from two major indices: the DOW 30 and a market-cap-weighted subset of 50 constituents from the S&P 100.","known_id":"wrds"},{"name":"Five macroeconomic indicators","provider":"FRED","kind":"macro","access":"public","period":"January 2010 to December 2023","universe":null,"quote":"The financial data, obtained from WRDS, is complemented by five macroeconomic indicators from FRED, selected based on their documented predictive power in asset pricing.","known_id":"fred"}],"known":[{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"The ﬁnancial data, obtained from WRDS, is complemented by ﬁve macroeconomic indicators from FRED, selected based on their documented predictive power in asset pricing: weekly initial jobless claims (ICSA), consumer sentiment (UMCSENT), new home sales (HSN1F), unemployment rate (UNRATE), and high-yield bond spread (HYBS).","mentions":1,"used_in":1},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"The ﬁnancial data, obtained from WRDS, is complemented by ﬁve macroeconomic indicators from FRED, selected based on their documented predictive power in asset pricing: weekly initial jobless claims (ICSA), consumer sentiment (UMCSENT), new home sales (HSN1F), unemployment rate (UNRATE), and high-yield bond spread (HYBS).","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"S&P 100 and DOW 30 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":"DINN consistently outperforms state-of-the-art deep learning models on both S&P 100 and DOW 30 datasets.","kind":"performance","quote":"Extensive experiments on S&P100 and DOW30 datasets show that our model consistently outperforms state-of-the-art deep learning models."},{"finding":"During the COVID-19 period, DINN-selected portfolios achieve Sharpe ratios of 1.14 (S&P 100) and 0.87 (DOW 30), higher than non-selected portfolios (0.59 and 0.58).","kind":"performance","quote":"During the COVID-19 period, DINN-selected portfolios achieve an SR of 1.14 for the S&P 100 and 0.87 for the DOW 30, exceeding the SR of portfolios formed from non-selected stocks (0.59 and 0.58, respectively)."},{"finding":"High‑sensitivity assets (large gradient |∂ŵ/∂µ|) exhibit lower mean‑squared error than low‑sensitivity assets, indicating the model learns what matters.","kind":"predictive-accuracy","quote":"high-sensitivity assets actually show lower MSE. This occurs because DINN allocates greater learning capacity to stocks where prediction errors would result in higher decision-related costs."},{"finding":"The prob‑sparse attention mechanism helps the model focus on a smaller subset of assets, yielding lower drawdowns and higher risk‑adjusted performance in stress regimes.","kind":"performance","quote":"The inclusion of a prob-sparse attention mechanism may helps the model identify and emphasize a smaller subset of assets critical to replicating market dynamics under a variety of macroeconomic conditions."}],"reported_performance":{"strategy":"Decision-Informed Neural Network (DINN)","sharpe":1.29,"sharpe_benchmark":null,"annual_return_pct":63.25,"total_return_pct":null,"max_drawdown_pct":39.51},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":57,"citations":{"cited_by_in_corpus":9,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":7},"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":"2026-11-14T17:46:14Z"},"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/"}