{"paper_id":"2409.06724","title":"MLP, XGBoost, KAN, TDNN, and LSTM-GRU Hybrid RNN with Attention for SPX and NDX European Call Option Pricing","authors":["Boris Ter-Avanesov","Homayoon Beigi"],"paper_date":"2024-08-26","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.06724v3","page_url":"https://thequant.space/flowcharts/mlp-xgboost-kan-tdnn-and-lstm-gru-hybrid-rnn-with-attent/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using several artificial neural network architectures, including MLP, KAN, TDNN, and an LSTM‑GRU hybrid RNN with attention, to price European call options.","quote":"We explore the performance of various artificial neural network architectures, including a multilayer perceptron (MLP), Kolmogorov‑Arnold network (KAN), LSTM‑GRU hybrid recursive neural network (RNN) models, and a time‑delay neural network (TDNN) for pricing European call options.","summary":"We explore the performance of various artificial neural network architectures, including a multilayer perceptron (MLP), Kolmogorov-Arnold network (KAN), LSTM-GRU hybrid recursive neural network (RNN) models, and a time-delay neural network (TDNN) for pricing European call options. In this study, we…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"No transaction costs or taxes","type":"market","stated":"explicit","quote":"1. No transaction costs or taxes"},{"assumption":"No riskless arbitrage can exist","type":"market","stated":"explicit","quote":"2. No riskless arbitrage can exist"},{"assumption":"No dividends or other cash flows are paid during the lifetime of the security","type":"market","stated":"explicit","quote":"3. No dividends or other cash flows are paid during the lifetime of the security"},{"assumption":"Trading and hedging of security is continuous, with the asset’s liquidity being guaranteed","type":"execution","stated":"explicit","quote":"4. Trading and hedging of security is continuous, with the asset’s liquidity being guaranteed"},{"assumption":"Risk‑free rate is constant for all maturities","type":"model","stated":"explicit","quote":"5. Risk‑free rate is constant for all maturities"},{"assumption":"Stock price follows Geometric Brownian motion with constant volatility over the option’s life","type":"model","stated":"explicit","quote":"7. Stock price follows Geometric Brownian motion with volatility of the underlying asset being constant over the lifetime of the option."}]},"datasets":{"status":"available","items":[{"name":"OptionMetrics IvyDB US (subset df)","provider":"OptionMetrics via Wharton Research Data Services","kind":"options","access":"commercial","period":"2015/05/13 to 2023/02/28","universe":"European call options on SPX and NDX indices","quote":"The data for this study comes from the Wharton Research Data Services as a subset of the (optionm_all) IvyDB US by OptionMetrics data set","known_id":"wrds"}],"known":[{"id":"optionmetrics","name":"OptionMetrics IvyDB","provider":"OptionMetrics","kind":"options","access":"commercial","quote":"4.1 Data Setup The data for this study comes from the Wharton Research Data Services as a subset of the (optionm_all) IvyDB US by OptionMetrics data set.","mentions":6,"used_in":3},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"4.1 Data Setup The data for this study comes from the Wharton Research Data Services as a subset of the (optionm_all) IvyDB US by OptionMetrics data set.","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The ’target_C/K’ column is then found by dividing the calculated C by the calculated K. Data for the underlying indices’ clos-ing prices (daily) is collected from Yahoo Finance for the same date range.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":true},"conflict_kind":"applicability","card_detail":null,"card_quote":"1. No transaction costs or taxes","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The LSTM‑GRU hybrid RNN model with attention achieves the lowest error among all models, with MSE 0.000021, RMSE 0.004583, MAE 0.003301.","kind":"performance","quote":"(1) Best RNN 0.000021 0.004583 0.003301"},{"finding":"The KAN model outperforms the TDNN and MLP models.","kind":"performance","quote":"Also, the KAN model outperforms the TDNN and MLP models."},{"finding":"The Black‑Scholes model performs far worse than the machine‑learning models, with MSE 0.003142, RMSE 0.056056, MAE 0.018677.","kind":"performance","quote":"(6) Best BS 0.003142 0.056056 0.018677"},{"finding":"Best XGBoost model achieves MSE 0.000025, RMSE 0.005021, MAE 0.003660, better than MLP but worse than RNN and KAN.","kind":"performance","quote":"(2) Best XGBoost 0.000025 0.005021 0.003660"},{"finding":"Best MLP model achieves MSE 0.000056, RMSE 0.007449, MAE 0.005483.","kind":"performance","quote":"(4) Best MLP 0.000056 0.007449 0.005483"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":50,"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":"2026-11-14T18:03:22Z"},"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/"}