{"paper_id":"2306.10582","title":"Machine Learning and Hamilton-Jacobi-Bellman Equation for Optimal Decumulation: a Comparison Study","authors":["Marc Chen","Mohammad Shirazi","Peter A. Forsyth","Yuying Li"],"paper_date":"2023-06-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.10582v1","page_url":"https://thequant.space/flowcharts/machine-learning-and-hamilton-jacobi-bellman-equation-for-op/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel data‑driven neural network optimization framework to solve a stochastic control problem with constraints for DC pension decumulation.","quote":"We propose a novel data-driven neural network (NN) optimization framework for solving an optimal stochastic control problem under stochastic constraints.","summary":"We propose a novel data-driven neural network (NN) optimization framework for solving an optimal stochastic control problem under stochastic constraints. Customized activation functions for the output layers of the NN are applied, which permits training via standard unconstrained optimization. The…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"No taxes are incurred on rebalancing.","type":"execution","stated":"explicit","quote":"We assume no taxes are incurred on rebalancing, which is reasonable since retirement accounts are"},{"assumption":"Transaction costs are negligible.","type":"execution","stated":"explicit","quote":"In addition, since trading is infrequent, we assume transaction costs to be negligible (Dang and Forsyth, 2014)."},{"assumption":"Instantaneous rebalancing (no price changes between withdrawal and allocation).","type":"execution","stated":"explicit","quote":"We assume instantaneous rebalancing, which means there are no changes in asset prices in the interval (t−i ,t+i )."},{"assumption":"Log of jump multiplier follows a double exponential distribution.","type":"model","stated":"explicit","quote":"We assume that log(ξs) follows a double exponential distribution (Kou, 2002; Kou and Wang, 2004)."},{"assumption":"Controls depend only on wealth (no transaction costs).","type":"model","stated":"explicit","quote":"As formulated, the controls depend on wealth only (see Forsyth (2022) for a proof, assuming no transaction costs)."},{"assumption":"Synthetic data are generated from calibrated parametric SDE models.","type":"data","stated":"explicit","quote":"Any data set referred to in this paper as synthetic data is generated by parametric stochastic models (SDEs)"}]},"datasets":{"status":"available","items":[{"name":"CRSP monthly data (bond and stock indices)","provider":"CRSP","kind":"market-prices","access":"commercial","period":"1926:1-2019:12","universe":"CRSP 10‑year U.S. Treasury index (bond) and CRSP value‑weighted total return index (stock)","quote":"For the computational study in this paper, we use data from the Center for Research in Security Prices (CRSP) on a monthly basis over the 1926:1-2019:12 period.","known_id":"crsp"}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"in this paper, we use data from the Center for Research in Security Prices (CRSP) on a monthly basis over the 1926:1-2019:12 period.4 The specific indices used are the CRSP 10-year U.S. Treasury index for the bond asset5 and the CRSP value-weighted total return index for the stock asset6.","mentions":24,"used_in":5}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"In addition, since trading is infrequent, we assume transaction costs to be negligible (Dang and Forsyth, 2014).","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"In addition, since trading is infrequent, we assume transaction costs to be negligible (Dang and Forsyth, 2014).","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"The NN framework yields a solution that closely matches the ground‑truth HJB PDE results.","kind":"theoretical","quote":"We demonstrate that the proposed NN framework produced solution accurately approximates the ground truth solution."},{"finding":"Out‑of‑sample tests show almost unchanged performance compared to training results.","kind":"performance","quote":"Out‑of‑sample tests involve testing model performance on an unseen data set"},{"finding":"The NN can accurately approximate a bang‑bang control despite its discontinuity.","kind":"theoretical","quote":"the continuous function approximation from the NN framework is able to approximate a bang‑bang control with high accuracy."},{"finding":"The NN allocation control maintains a low‑risk profile, with the 95th percentile stock allocation never exceeding 40%.","kind":"performance","quote":"the maximum stock allocation for the 95th percentile never exceeds 40%, indicating that this is a stable low‑risk strategy."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":"2026-11-14T18:25:40Z"},"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/"}