{"paper_id":"2509.01393","title":"Adaptive Alpha Weighting with PPO: Enhancing Prompt-Based LLM-Generated Alphas in Quant Trading","authors":["Qizhao Chen","Hiroaki Kawashima"],"paper_date":"2025-09-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.01393v1","page_url":"https://thequant.space/flowcharts/adaptive-alpha-weighting-with-ppo-enhancing-prompt-based-ll/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a reinforcement learning framework using Proximal Policy Optimization to dynamically weight multiple LLM‑generated formulaic alphas for stock trading.","quote":"This paper introduces a reinforcement learning framework that employs Proximal Policy Optimization (PPO) to dynamically optimize the weights of multiple large language model (LLM)-generated formulaic alphas for stock trading strategies.","summary":"This paper proposes a reinforcement learning framework that employs Proximal Policy Optimization (PPO) to dynamically optimize the weights of multiple large language model (LLM)-generated formulaic alphas for stock trading strategies. Formulaic alphas are mathematically defined trading signals…","strategy":"PPO-optimized LLM-generated alpha portfolio"},"assumptions":{"status":"available","items":[{"assumption":"Trades are executed at the closing price of day t with no information beyond day t.","type":"execution","stated":"explicit","quote":"at the close price of day t, and no information beyond day t is used when determining trading positions."},{"assumption":"Positions are held from day t to day t+1 and returns are realized using the next‑day return.","type":"execution","stated":"explicit","quote":"... Trades are assumed to be executed immediately after the decision at day t, and the resulting position pt is held over the interval from day t to day t + 1."},{"assumption":"Alpha signals are normalized to approximately a standard normal distribution.","type":"model","stated":"explicit","quote":"αi,t Alpha signals Normalized to ∼N(0, 1)"},{"assumption":"A soft penalty is applied when the position sign conflicts with a regime indicator defined by moving‑average crossover.","type":"market","stated":"explicit","quote":"The market regime indicator regimet ∈{0, 1} is defined based on the moving-average crossover, where regimet = 1 denotes a bullish regime (20-day MA above 100-day MA) and regimet = 0 indicates a bearish regime."},{"assumption":"Transaction costs are a fixed 0.1% per trade.","type":"execution","stated":"explicit","quote":"TCt Transaction cost per trade 0.001"},{"assumption":"Volatility targeting scales positions to keep annualized volatility near 15%.","type":"model","stated":"explicit","quote":"σtarget Annualized volatility target 0.15 (fixed)"}]},"datasets":{"status":"available","items":[{"name":"Ten selected stocks","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"ten stocks (e.g., Apple, HSBC, Pepsi, etc.)","quote":"we leverage a DeepSeek model to generate fifty alphas for ten stocks"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Historical stock price data from 2016/02/16 to 2024/05/08 are obtained using the yfinance Python library.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"US stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Fixed cost of 0.001 (0.1%) per trade is included in the reward calculation.","quote":"TCt Transaction cost per trade 0.001","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Fixed cost of 0.001 (0.1%) per trade is included in the reward calculation.","card_quote":"TCt Transaction cost per trade 0.001","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The PPO‑adjusted strategy does not consistently achieve the highest cumulative returns but attains higher Sharpe ratios and lower maximum drawdowns in most cases.","kind":"performance","quote":"Experimental results indicate that the PPO‑optimized strategy does not consistently deliver the highest cumulative returns across all stocks, but it achieves comparatively higher Sharpe ratios and smaller maximum drawdowns in most cases."},{"finding":"Sharpe ratio improvements over buy‑and‑hold are statistically significant for several stocks (e.g., Apple +1.77, HSBC +0.79).","kind":"performance","quote":"Apple 1.7695* [0.1787, 3.4424] 0.0296 ... HSBC 0.7928* [0.4321, 2.2641] 0.0006"},{"finding":"Diebold‑Mariano tests show negative DM statistics, indicating PPO outperforms baseline strategies for many stocks.","kind":"statistical","quote":"A negative DM stat indicates PPO outperforms the benchmark."},{"finding":"Average daily turnover remains low for most stocks (e.g., Netflix 0.0090) suggesting limited impact of transaction costs.","kind":"performance","quote":"Average daily turnover remains low for several stocks, including Netflix (0.0090) and HSBC (0.0348), and reaches its highest level for Airbus (0.2007)."},{"finding":"Ablation analysis shows that reducing the number of alphas can slightly improve cumulative return and Sharpe for some stocks but may worsen performance for others.","kind":"other","quote":"reducing the number of alphas leads to slight improvements in both cumulative return and Sharpe ratio for certain stocks. However, for others, their performance may worsen after reducing the number of alphas."}],"reported_performance":{"strategy":"PPO-optimized LLM-generated alpha portfolio","sharpe":2.4113,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":1.01},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":57,"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":"2026-11-14T16:38:21Z"},"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/"}