{"paper_id":"2511.17963","title":"Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization","authors":["Jun Kevin","Pujianto Yugopuspito"],"paper_date":"2025-11-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.17963v1","page_url":"https://thequant.space/flowcharts/hybrid-lstm-and-ppo-networks-for-dynamic-portfolio-optimizat/","scores":{"empirical_rigor":7.5,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid portfolio optimization framework that combines LSTM forecasting with PPO reinforcement learning for dynamic allocation.","quote":"This paper introduces a hybrid framework for portfolio optimization that fuses Long Short-Term Memory (LSTM) forecasting with a Proximal Policy Optimization (PPO) reinforcement learning strategy.","summary":"This paper introduces a hybrid framework for portfolio optimization that fuses Long Short-Term Memory (LSTM) forecasting with a Proximal Policy Optimization (PPO) reinforcement learning strategy. The proposed system leverages the predictive power of deep recurrent networks to capture temporal…","strategy":"Hybrid LSTM+PPO (Top-5)"},"assumptions":{"status":"available","items":[{"assumption":"Transaction costs are modeled as a flat 0.1% turnover cost applied during portfolio evaluation.","type":"execution","stated":"implied","quote":"Transaction costs are not applied at this stage; a 0.1% turnover cost is later included during portfolio evaluation to isolate the LSTM’s predictive effect."},{"assumption":"Data are split chronologically into 70% training and 30% testing for strict out‑of‑sample evaluation.","type":"data","stated":"implied","quote":"The dataset is then chronologically divided into 70% training and 30% testing subsets to maintain strict out-of-sample evaluation."},{"assumption":"Missing values are forward‑filled and returns are computed as log‑returns to improve stationarity.","type":"data","stated":"implied","quote":"Missing values were forward-filled, trading calendars synchronized, and closing prices transformed into log-returns"},{"assumption":"All price data are sourced from Yahoo Finance and resampled to weekly intervals.","type":"market","stated":"implied","quote":"All data were sourced from Yahoo Finance (2018–2024) at daily frequency and resampled to weekly intervals."},{"assumption":"The PPO agent operates in continuous action spaces and uses a clipped‑surrogate reward based on cumulative return and Sharpe ratio.","type":"model","stated":"implied","quote":"these signals into sparse portfolio weights that maximize cumulative net return under transaction cost and turnover constraints."}]},"datasets":{"status":"available","items":[{"name":"U.S. equities (Nasdaq‑100)","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2018–2024","universe":"Nasdaq‑100 constituents","quote":"... All data were sourced from Yahoo Finance (2018–2024) at daily frequency","known_id":"yahoo-finance"},{"name":"Indonesian equities (IDX30)","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2018–2024","universe":"IDX30 constituents","quote":"... All data were sourced from Yahoo Finance (2018–2024) at daily frequency","known_id":"yahoo-finance"},{"name":"U.S. 10‑Year Treasury yields (ˆTNX)","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2018–2024","universe":"U.S. Treasury yields","quote":"... All data were sourced from Yahoo Finance (2018–2024) at daily frequency","known_id":"yahoo-finance"},{"name":"Top 10 cryptocurrencies by market cap","provider":"Yahoo Finance","kind":"crypto-onchain","access":"public","period":"2018–2024","universe":"Bitcoin, Ethereum, XRP, Binance Coin, etc.","quote":"... All data were sourced from Yahoo Finance (2018–2024) at daily frequency","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"All data were sourced from Yahoo Finance (2018–2024) at daily frequency and resampled to weekly intervals.","mentions":1,"used_in":1}],"sample":{"start":"2024-01","end":"2024-12","market":"multi-asset (U.S. equities, Indonesian equities, bonds, cryp","asset_class":"multi-asset","frequency":"weekly"},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat 0.1% turnover cost is applied during portfolio evaluation; results are reported net of transaction costs where applicable.","quote":"Transaction costs are not applied at this stage; a 0.1% turnover cost is later included during portfolio evaluation to isolate the LSTM’s predictive effect.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat 0.1% turnover cost is applied during portfolio evaluation; results are reported net of transaction costs where applicable.","card_quote":"Transaction costs are not applied at this stage; a 0.1% turnover cost is later included during portfolio evaluation to isolate the LSTM’s predictive effect.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The Hybrid LSTM+PPO Top‑5 portfolio achieves the highest annualized return of 25.4%, outperforming all single‑model and benchmark strategies.","kind":"performance","quote":"Hybrid LSTM+PPO (Top-5) portfolio achieves the highest annualized return (25.4%), outperforming both stand-alone LSTM and PPO models as well as passive benchmarks."},{"finding":"Increasing the Top‑K diversification level reduces maximum drawdown, with Top‑30 achieving the shallowest drawdown of –10.6%.","kind":"performance","quote":"The maximum drawdowns (MDD) occur around mid-2024, reaching approximately −13.7%, −12.0%, and −10.6% for Top-5, Top-10, and Top-30 respectively."},{"finding":"LSTM‑only strategies perform poorly at low K values, showing negative returns and high drawdowns, highlighting the limitation of static predictive models without adaptive allocation.","kind":"performance","quote":"The LSTM-only strategies, while capable of capturing temporal dependencies, perform poorly at smaller K values due to limited diversification and their static allocation nature."}],"reported_performance":{"strategy":"Hybrid LSTM+PPO (Top-5)","sharpe":0.9565,"sharpe_benchmark":null,"annual_return_pct":25.38,"total_return_pct":null,"max_drawdown_pct":13.69},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":40,"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":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":"2026-11-14T17:21:17Z"},"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/"}