{"paper_id":"2510.27132","title":"Exact Terminal Condition Neural Network for American Option Pricing Based on the Black-Scholes-Merton Equations","authors":["Wenxuan Zhang","Yixiao Guo","Benzhuo Lu"],"paper_date":"2025-10-31","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.27132v1","page_url":"https://thequant.space/flowcharts/exact-terminal-condition-neural-network-for-american-option/","scores":{"empirical_rigor":7,"math_complexity":9,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Exact Terminal Condition Neural Network (ETCNN), a deep learning framework for accurately pricing American options by solving the Black‑Scholes‑Merton equations.","quote":"This paper proposes the Exact Terminal Condition Neural Network (ETCNN), a deep learning framework for accurately pricing American options by solving the Black‑Scholes‑Merton (BSM) equations.","summary":"This paper proposes the Exact Terminal Condition Neural Network (ETCNN), a deep learning framework for accurately pricing American options by solving the Black-Scholes-Merton (BSM) equations. The ETCNN incorporates carefully designed functions that ensure the numerical solution not only exactly…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The risk‑free rate r is constant under the BSM model.","type":"model","stated":"explicit","quote":"where r is the risk‑free rate and is assumed to be a constant under the BSM model."},{"assumption":"Volatility σ and drift µ are constant over time in the geometric Brownian motion.","type":"model","stated":"explicit","quote":"Both σ and r are expressed in annualized terms. In the geometric Brownian motion framework, the drift and volatility are assumed to remain constant."},{"assumption":"The portfolio is self‑financing, i.e., changes come only from gains/losses on the underlying securities.","type":"execution","stated":"explicit","quote":"The self‑financing assumption implies that changes in the portfolio are solely attributed to gains or losses in the underlying securities, with no impact from changes in the holdings"}]},"datasets":{"status":"available","items":[{"name":"Binomial tree reference solution (N = 4000 steps)","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"The binomial tree method with N = 4000 steps is employed to compute the reference solution, serving as the benchmark for accuracy evaluation."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"ETCNN outperforms other methods across most scenarios, especially in high‑volatility markets.","kind":"performance","quote":"The results demonstrate that the proposed ETCNN outperforms other methods across most of the various scenarios, particularly in high‑volatility markets."},{"finding":"Compared to PINN, ETCNN reduces L2 error by roughly an order of magnitude.","kind":"performance","quote":"Compared to PINN, ETCNN achieves a reduction in L2 error by an order of magnitude."},{"finding":"The early‑exercise boundary from ETCNN aligns almost perfectly with the true boundary, unlike PINN which deviates.","kind":"performance","quote":"The early exercise boundary derived from ETCNN closely aligns with the true early exercise"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"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":"2026-11-14T17:23:05Z"},"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/"}