{"paper_id":"2411.09899","title":"Portfolio Optimization with Feedback Strategies Based on Artificial Neural Networks","authors":["Yaacov Kopeliovich","Michael Pokojovy"],"paper_date":"2024-11-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.09899v1","page_url":"https://thequant.space/flowcharts/portfolio-optimization-with-feedback-strategies-based-on-art/","scores":{"empirical_rigor":7,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a deep‑learning framework that uses empirical utility maximization with artificial neural networks to obtain optimal dynamic portfolio allocation without deriving or solving the Hamilton‑Jacobi‑Bellman equation.","quote":"While most existing research has primarily focused on how DL can alleviate the curse of dimensionality when solving the Hamilton-Jacobi-Bellman (HJB) equation, some very recent developments propose to forego derivation and solution of HJB in favor of empirical utility maximization over dynamic allocation strategies expressed through ANN. In other words, we consider the Merton problem and attempt to apply AI tools","summary":"With the recent advancements in machine learning (ML), artificial neural networks (ANN) are starting to play an increasingly important role in quantitative finance. Dynamic portfolio optimization is among many problems that have significantly benefited from a wider adoption of deep learning (DL).…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The risky asset follows either a geometric Brownian motion or a Heston stochastic volatility model.","type":"model","stated":"explicit","quote":"To showcase the method, we apply it to optimal portfolio allocation between a cash account and the S&P 500 index modeled using geometric Brownian motion or the Heston model. Examples We present two application examples to showcase how the DL approach from Section 3 can be applied to optimal portfolio problem (1)–(7) when the risky asset is modeled using geometric Brownian motion (Section 4.1) or Heston model","support":"full"},{"assumption":"The risk‑free rate is constant at 5% per annum.","type":"market","stated":"explicit","quote":"The risk-free rate was set at 5% p.a.","support":"full"},{"assumption":"Initial wealth is set to $1.0.","type":"other","stated":"explicit","quote":"The initial wealth was set at $1.0.","support":"full"},{"assumption":"Three years of adjusted daily closing prices (1/1/2021–12/31/2023) are used for calibration of the market models.","type":"data","stated":"explicit","quote":"Three years’ worth of adjusted daily closing prices (1/1/2021–12/31/2023) were used for calibration purposes3 as detailed below.","support":"full"},{"assumption":"Synthetic market paths can be generated arbitrarily many times for training the ANN.","type":"statistical","stated":"explicit","quote":"(21) 3Note that the number of data points (753 here) used for model calibration does not limit our ability to simulate arbitrarily many synthetic paths to train the ANN model.","support":"full"},{"assumption":"Training, test and validation splits are used to avoid over‑training.","type":"execution","stated":"explicit","quote":"However, utilization of data splitting into training, test and validation segments is crucial to protect against overtraining.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 adjusted daily closing prices","provider":null,"kind":"market-prices","access":"public","period":"2021-01-01 to 2023-12-31","universe":"S&P 500 index","quote":"In both situations, the S&P 500 index (GSPC ticker) was selected as risky asset, while VIX index was used to calibrate Heston volatility process. Three years’ worth of adjusted daily closing prices (1/1/2021–12/31/2023) were used for calibration purposes3 as detailed below.","support":"full"},{"name":"VIX index data","provider":null,"kind":"market-prices","access":"public","period":"2021-01-01 to 2023-12-31","universe":"VIX index","quote":"In both situations, the S&P 500 index (GSPC ticker) was selected as risky asset, while VIX index was used to calibrate Heston volatility process.","support":"partial"},{"name":"Synthetic market paths (GBM and Heston)","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"To avoid overtraining, minibatches were re-simulated at each step. (21) 3Note that the number of data points (753 here) used for model calibration does not limit our ability to simulate arbitrarily many synthetic paths to train the ANN model.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"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":"none","findings":[{"finding":"For both GBM and Heston models, the ANN‑based allocation yields expected utility on par with the analytic optimal weights.","kind":"performance","quote":"Good agreement with the analytic optimum can 8 0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.2 0.4 0.6 0.8 1.0 1/ η Stock Weight Theoretical ANN Figure 2: Merton ratio vs 1/η. be observed. Again, the expected utility under ANN was on par with that under the analytic weight from Equation (22) over the range of η’s considered.","support":"full"},{"finding":"Training the ANN required 27,000 (GBM) to 45,000 (Heston) gradient evaluations, far fewer than the 2.56 million simulations used in prior work.","kind":"performance","quote":"While van Staden et al. (2023) required 2.56 million replications, 27,000 (for GBM) to 45,000 (for Heston) gradient evaluations were sufficient in our simulations.","support":"full"},{"finding":"The total training time was less than 6 hours.","kind":"performance","quote":"The training time was less than 6 hrs.","support":"full"},{"finding":"With only 3–5 hidden neurons in a single hidden layer, the ANN reproduces analytic portfolio weights and utility values consistently.","kind":"performance","quote":"With only 3-5 hidden neurons and a single hidden layer, the ANN results appeared to be consistent with the analytic ones both in terms of portfolio weights and expected utility values.","support":"full"},{"finding":"All algorithms were implemented in plain R code without third‑party deep‑learning libraries or GPU acceleration.","kind":"other","quote":"All algorithm were implemented in plain R code and run in RStudio under 64-bit Windows 11 Pro OS on a Dell Precision 3581 laptop with 13th Gen Intel(R) Core(TM) i7-13800H 2.50 GHz CPU and 32 GB RAM. No third-party DL libraries or GPU acceleration were employed. 4.1.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":28,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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/mpokojovy/StochVolPortfolioML","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":2,"extracted_at":"2026-11-14T19:54:02Z"},"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/"}