{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T09:03:13Z","timestamp":1790240593026,"version":"4.1.0"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Accurate forecasting of equity market volatility is essential for risk management, portfolio allocation, and derivative pricing. From a machine learning and soft-computing perspective, this paper investigates the relative predictive role of idiosyncratic and systematic jump risks in forecasting realized volatility across major U.S. equity market sectors, considering both volatility levels and directional movements. We conduct a comprehensive out-of-sample comparison of linear benchmark models and a broad set of machine learning methods. The results show that selected machine-learning models improve forecasting accuracy relative to HAR, but the gains depend on the sector and algorithm, and HAR remains a competitive benchmark. Feature importance analysis indicates that systematic jump risk contributes more strongly to volatility predictability than idiosyncratic jump risk. To further capture nonlinear and timevarying market dynamics, we propose novel regime-dependent predictors derived from a Markov regimeswitching framework and incorporate them into the learning process. These regime-sensitive features lead to a marked improvement in forecasting performance, particularly for volatility direction prediction. Overall, the findings demonstrate that integrating jump-based feature engineering and regime-dependent information within machine learning frameworks yields more accurate and robust volatility forecasts.<\/jats:p>","DOI":"10.2139\/ssrn.7507178","type":"posted-content","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T08:20:14Z","timestamp":1790238014000},"source":"Crossref","is-referenced-by-count":0,"title":["Forecasting Realized Volatility Using Idiosyncratic and Systematic Jump Risks: A Machine Learning Approach with Market Regimes"],"prefix":"10.2139","author":[{"given":"Weijia","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eman","family":"Abdelfattah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T08:20:14Z","timestamp":1790238014000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7507178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7507178","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}