{"paper_id":"2502.07868","title":"Minimal Shortfall Strategies for Liquidation of a Basket of Stocks using Reinforcement Learning","authors":["Moustapha Pemy","Na Zhang"],"paper_date":"2025-02-11","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.07868v1","page_url":"https://thequant.space/flowcharts/minimal-shortfall-strategies-for-liquidation-of-a-basket-of/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a minimal shortfall algorithm that uses reinforcement learning to jointly train two neural networks for optimal liquidation of highly correlated stocks.","quote":"We propose a novel method based on stochastic optimal control to optimally tackle this complex multidimensional problem. The proposed method minimizes the overall execution shortfall of highly correlated stocks using a reinforcement learning approach.","summary":"This paper studies the ubiquitous problem of liquidating large quantities of highly correlated stocks, a task frequently encountered by institutional investors and proprietary trading firms. Traditional methods in this setting suffer from the curse of dimensionality, making them impractical for…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The Markov Decision Process under any policy is irreducible and aperiodic.","type":"model","stated":"explicit","quote":"(A1): We assume that under any policy π = (ak)k our Markov Decision Process is irreducible and aperiodic."},{"assumption":"The policy function is differentiable with respect to its neural‑network parameters.","type":"model","stated":"explicit","quote":"(A2): We assume that our policy function π(x, a, θ) is differentiable with respect to θ."},{"assumption":"Stock prices follow a discrete‑time geometric Brownian motion.","type":"model","stated":"explicit","quote":"the environment in which we train our neural networks is a discrete-time controlled dynamical system where stock prices follow a discrete version of the geometric Brownian motion"},{"assumption":"All stocks to be liquidated are highly correlated.","type":"market","stated":"explicit","quote":"we assume without loss of generality that those stocks are correlated and we will use their correlation to our advantage"},{"assumption":"Trading actions incur a linear market impact.","type":"execution","stated":"explicit","quote":"we assume the stocks we want to liquidate are highly correlated and that our trading actions will incur a linear market impact."},{"assumption":"Maximum trade size per stock is bounded by a fixed threshold Mi.","type":"execution","stated":"explicit","quote":"For each of these stock we have a threshold Mi that we can traded at once without been detected."}]},"datasets":{"status":"available","items":[{"name":"Intra‑day market data (week of September 5‑8 2017)","provider":null,"kind":"market-prices","access":"unknown","period":"2017-09-05 to 2017-09-08","universe":null,"quote":"For the week of September 5 to 8, 2017, the trading data of the first three days are used as training data and the trading data of the last day of the week are the testing data."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Linear market impact functions fi(x) = λi x with λi = −1 × 10⁻¹¹ for each stock.","quote":"the market impact functions are fi(x) = λix with λi = −1 × 10−11, i = 1, ..., 6.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Linear market impact functions fi(x) = λi x with λi = −1 × 10⁻¹¹ for each stock.","card_quote":"the market impact functions are fi(x) = λix with λi = −1 × 10−11, i = 1, ..., 6.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"execution-cost","findings":[{"finding":"The proposed reinforcement‑learning methodology achieves its intended objectives, minimizing execution shortfall and tracking error, and can be implemented in software.","kind":"performance","quote":"We can see that our methodology clearly achieves its intended objectives and can be effectively implemented in a software package."},{"finding":"The authors rigorously establish convergence of the optimal trading strategy.","kind":"theoretical","quote":"We rigorously establish the convergence of our optimal trading strategy"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"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":true,"code_url":"https://github.com/mpemy/optimaltradingml","note":null},"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":"2026-11-14T17:45:46Z"},"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/"}