{"paper_id":"2510.22348","title":"Causal and Predictive Modeling of Short-Horizon Market Risk and Systematic Alpha Generation Using Hybrid Machine Learning Ensembles","authors":["Aryan Ranjan"],"paper_date":"2025-10-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.22348v1","page_url":"https://thequant.space/flowcharts/causal-and-predictive-modeling-of-short-horizon-market-risk/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a systematic trading framework that forecasts short‑horizon market risk and generates alpha using a hybrid machine learning ensemble of neural networks and tree‑based models.","quote":"We present a systematic trading framework that forecasts short-horizon market risk, identifies its underlying drivers, and generates alpha using a hybrid machine learning ensemble built to trade on the resulting signal.","summary":"We present a systematic trading framework that forecasts short-horizon market risk, identifies its underlying drivers, and generates alpha using a hybrid machine learning ensemble built to trade on the resulting signal. The framework integrates neural networks with tree-based voting models to…","strategy":"Hybrid machine learning ensemble long/short risk‑managed strategy"},"assumptions":{"status":"available","items":[{"assumption":"The dataset contains only 5,000–6,000 daily observations after filtering, limiting effective sample size.","type":"data","stated":"explicit","quote":"A shallow network mitigates overfitting while still capturing temporal dependencies."},{"assumption":"Trading results are reported without accounting for transaction costs.","type":"execution","stated":"explicit","quote":"Note: These metrics do not currently account for transaction costs nor have they been forward tested."},{"assumption":"Model performance metrics are based on in‑sample (in‑time) evaluation, not out‑of‑sample.","type":"statistical","stated":"explicit","quote":"Metrics such as ROC-AUC, precision, and recall therefore reflect in-sample performance."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 ETF (SPY) daily price data","provider":null,"kind":"market-prices","access":"unknown","period":"2005-2025","universe":"S&P 500 ETF","quote":"predict five-day drawdowns in the S&P 500 ETF (SPY), leveraging a cross-asset feature set spanning equities, fixed income, foreign exchange, commodities, and volatility markets."}],"known":[],"sample":{"start":"2005","end":"2025","market":"S&P 500 ETF (SPY)","asset_class":"multi-asset","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":"Note: These metrics do not currently account for transaction costs nor have they been forward tested.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Note: These metrics do not currently account for transaction costs nor have they been forward tested.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The hybrid ensemble achieves a Sharpe ratio of 2.51, an annualized CAPM alpha of +0.28, and a market beta of 0.51 over the 2005‑2025 backtest.","kind":"performance","quote":"Empirical results show a Sharpe ratio of 2.51 and an annualized CAPM alpha of +0.28, with a market beta of 0.51, indicating that the model delivers substantial systematic alpha with limited directional exposure during the 2005–2025 backtest period."},{"finding":"In‑sample classification yields 0.95 overall accuracy, with class‑0 recall of 0.99 and class‑1 recall of 0.82.","kind":"predictive-accuracy","quote":"Class 0 recall of 0.99 indicates that the m…"},{"finding":"The strategy’s information ratio versus SPY is 1.73, maximum drawdown -18.12%, annualized return 40.84% and volatility 13.23%.","kind":"performance","quote":"Information Ratio vs SPY 1.73 ... Maximum Drawdown -18.12% ... Annualized Return 40.84% ... Annualized Volatility 13.23%"}],"reported_performance":{"strategy":"Hybrid machine learning ensemble long/short risk‑managed strategy","sharpe":2.51,"sharpe_benchmark":null,"annual_return_pct":40.84,"total_return_pct":null,"max_drawdown_pct":18.12},"out_of_sample":{"method":"none","headline_out_of_sample":false}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":31,"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":"2026-11-14T17:23:30Z"},"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/"}