{"paper_id":"2512.12250","title":"Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting","authors":["Anna Perekhodko","Robert Ślepaczuk"],"paper_date":"2025-12-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.12250v1","page_url":"https://thequant.space/flowcharts/stochastic-volatility-modelling-with-lstm-networks-a-hybrid/","scores":{"empirical_rigor":8.5,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid modelling framework that combines a Stochastic Volatility model with a Long Short‑Term Memory neural network for S&P 500 volatility forecasting.","quote":"This study proposes a hybrid modelling framework that integrates a Stochastic Volatility model with a Long Short Term Memory neural network.","summary":"Accurate volatility forecasting is essential in banking, investment, and risk management, because expectations about future market movements directly influence current decisions. This study proposes a hybrid modelling framework that integrates a Stochastic Volatility model with a Long Short Term…","strategy":"Hybrid SV-LSTM"},"assumptions":{"status":"available","items":[{"assumption":"Log‑returns are stationary, which is required for volatility modelling.","type":"statistical","stated":"explicit","quote":"enabling stationarity in the return series, a critical assumption for volatility modeling."},{"assumption":"The SV model parameters are estimated with weakly informative priors rather than strong priors.","type":"model","stated":"explicit","quote":"we adopt a data‑driven approach by employing weakly informative default priors, as inspired by Kim et al. (1998), rather than imposing strong prior distributions"},{"assumption":"Rolling‑window training uses the most recent 504 days to forecast the next day.","type":"execution","stated":"explicit","quote":"Model training and evaluation are conducted across 11 overlapping rolling windows covering the period from 2000 to 2024. For each window, the model is trained on the most recent 504 days and generates forecasts for the next day (t + 1)"},{"assumption":"Trading signals are generated at the daily close price with a flat transaction cost of 0.1% per side.","type":"execution","stated":"explicit","quote":"Transaction costs of 0.1% are applied at both entry and exit."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 daily closing prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"1998-01-01 to 2024-12-31","universe":"S&P 500 index","quote":"For the modeling of S&P 500 index volatility, the dataset consisted of daily closing prices obtained from Yahoo Finance, spanning January 1, 1998, to December 31, 2024.","known_id":"yahoo-finance"},{"name":"VIX monthly futures contracts","provider":"CBOE","kind":"options","access":"public","period":"2014-01 to 2024-12","universe":"VIX monthly futures","quote":"The selected data consisted of VIX monthly futures contracts, collected from the CBOE website for the entire testing period, from January 2014 to December 2024.","known_id":"cboe"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data used is daily close price for the S&P 500 index, covering the period from January 1, 1998, to December 31, 2024, obtained from the YahooFinance.","mentions":3,"used_in":3},{"id":"cboe","name":"Cboe","provider":"Cboe Global Markets","kind":"options","access":"commercial","quote":"7 Investment Strategy Simulation The selected data consisted of VIX monthly futures contracts, collected from the CBOE website for the entire testing period, from January 2014 to December 2024.","mentions":1,"used_in":1}],"sample":{"start":"2014-01","end":"2024-12","market":"S&P 500","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat fee of 0.1% is applied at both entry and exit of each VIX futures trade.","quote":"Transaction costs of 0.1% are applied at both entry and exit.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat fee of 0.1% is applied at both entry and exit of each VIX futures trade.","card_quote":"Transaction costs of 0.1% are applied at both entry and exit.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The hybrid SV‑LSTM model achieves a Mean Absolute Percentage Error of 4.75% on out‑of‑sample 21‑day rolling volatility forecasts (Jan 2014‑Dec 2024).","kind":"predictive-accuracy","quote":"The Mean Absolute Percentage Error (MAPE) of 4.75% indicates high relative accuracy and reflects the hybrid’s ability to closely track proportional volatility changes."},{"finding":"The hybrid model outperforms both standalone SV and LSTM models according to statistical tests (Diebold‑Mariano and Wilcoxon).","kind":"statistical","quote":"The error metrics demonstrated the superiority of the SV‑LSTM model over both the LSTM and SV models. Additionally, the Diebold‑Mariano (DM) test confirmed that the SV‑LSTM model exhibits better predictive accuracy than both benchmark models."},{"finding":"The investment‑strategy simulation using VIX futures shows that the SV‑LSTM signals generate cumulative equity curves that exceed naive long‑only and short‑only benchmarks.","kind":"performance","quote":"The investment strategy simulation further validated the practical relevance of the SV‑LSTM model by assessing its performance on VIX futures data spanning from 2014 to 2024 in a realistic market environment."}],"reported_performance":{"strategy":"Hybrid SV-LSTM","sharpe":-0.56,"sharpe_benchmark":null,"annual_return_pct":-14.57,"total_return_pct":-82,"max_drawdown_pct":85.15},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"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":true,"code_url":"https://github.com/aperekhodko/sv_lstm_hybrid_model","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":1,"extracted_at":"2026-11-14T17:18:58Z"},"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/"}