{"paper_id":"2410.10474","title":"European Option Pricing in Regime Switching Framework via Physics-Informed Residual Learning","authors":["Naman Krishna Pande","Puneet Pasricha","Arun Kumar","Arvind Kumar Gupta"],"paper_date":"2024-10-14","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2410.10474v1","page_url":"https://thequant.space/flowcharts/european-option-pricing-in-regime-switching-framework-via-ph/","scores":{"empirical_rigor":3,"math_complexity":8,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a physics-informed residual learning (PIRL) pricing method for European options in a regime‑switching framework.","quote":"we employ physics-informed residual learning (PIRL) and propose a pricing method for European options under a regime‑switching framework, where closed‑form solutions are not available.","summary":"In this article, we employ physics-informed residual learning (PIRL) and propose a pricing method for European options under a regime-switching framework, where closed-form solutions are not available. We demonstrate that the proposed approach serves an efficient alternative to competing pricing…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The financial market is frictionless with a cash account earning a constant risk‑free rate and one underlying asset.","type":"market","stated":"explicit","quote":"(a) a cash account that accrues interest at a constant risk‑free rate r, and (b) an underlying asset with price at time t denoted by St."},{"assumption":"The regime process X_t is a continuous‑time Markov chain with two states (bullish and bearish).","type":"model","stated":"explicit","quote":"We, further, assume that Xt is a continuous time Markov chain (CTMC) with two states"},{"assumption":"State transitions follow a Poisson process with intensity λ_jk.","type":"model","stated":"explicit","quote":"Since Xt is a CTMC, the transition between the two states occurs as a Poisson process, i.e., P(t*_{jk} > t) = e^{‑λ_{jk}t}, j, k = 1, 2, j̸= k."},{"assumption":"The risk related to a state transition is diversifiable and therefore unpriced.","type":"model","stated":"explicit","quote":"Following Zhu et al. (2012), we make the assumption that the risk related to a state transition is diversifiable and therefore unpriced, an assumption that does not compromise generality."},{"assumption":"The underlying Wiener process W_t and the regime process X_t are independent.","type":"model","stated":"explicit","quote":"the process {W_t} is the standard Wiener process and we assume that the processes X and W are independent."}]},"datasets":{"status":"available","items":[{"name":"Training data for BSM regime‑switching model","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Parameter Range… S0 [40, 100] r [0.01, 0.025] σ1 [0.10, 0.30] σ2 [σ1, 0.40] T [0, 4] t [0, T] Table 1: Sampling ranges for the parameters for generating the training data for BSM regime‑switching model."}],"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":"PIRL pricing of the regime‑switching BSM put option achieves very low out‑of‑sample errors (MAE ≈ 0.0092, MSE ≈ 0.0005).","kind":"predictive-accuracy","quote":"Figure 2 (a) and (b) 0.0092 0.0005 0.0092 0.0012 Figure 2 (c) 0.0152 0.0006 0.0225 0.0013"},{"finding":"For the regime‑switching Heston model, out‑of‑sample MAE/MSE range from 0.0199/0.0005 (ITM) to 0.0960/0.0135 (OTM).","kind":"predictive-accuracy","quote":"Table 6: Out of sample prediction errors for the Heston stochastic volatility with regime switching put option prices for ITM, ATM and OTM option types."},{"finding":"PIRL networks produce option price paths that closely match Monte‑Carlo benchmarks across time to expiry for ITM, ATM and OTM strikes.","kind":"pricing-calibration","quote":"Figure 4: European put option prices in the two regimes under Heston stochastic volatility model"},{"finding":"The trained PIRL models are nearly instantaneous to evaluate once trained, eliminating the need for retraining when parameters change.","kind":"performance","quote":"Specifically, we demonstrate that PIRLs eliminate the need for retraining and become nearly instantaneous once trained, thus, offering an efficient and flexible tool for pricing options across a broad range of specifications and parameters."}],"reported_performance":null,"out_of_sample":{"method":"holdout","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":"2026-11-14T17:59:06Z"},"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/"}