--- title: "FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis" canonical_url: "https://quantcalctools.com/guides/feds-paper-econometric-vs-machine-learning-models" publication: "QuantCalc Tools" domain: "quantcalctools.com" category: "broker-fees-and-calculators" published_at: "2026-10-31T16:30:27.546Z" updated_at: "2026-10-31T16:56:28.520Z" author: "Elena Rostova, FRM, CQF" author_credentials: "FRM, Certificate in Quantitative Finance (CQF)" reviewed_by: "QuantCalc Tools Editorial Fact-Checking Board" fact_check_passed: true tags: ["tools", "market-analysis", "feds-paper", "ymyl", "compliance"] citation_apa: "Elena Rostova, FRM, CQF. (2026). FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis. QuantCalc Tools. https://quantcalctools.com/guides/feds-paper-econometric-vs-machine-learning-models" --- # FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis > **Canonical Citation URL:** https://quantcalctools.com/guides/feds-paper-econometric-vs-machine-learning-models > **Publication:** QuantCalc Tools (https://quantcalctools.com) | **Category:** broker-fees-and-calculators | **Last Updated:** 2026-10-31T16:56:28.520Z > **Author:** Elena Rostova, FRM, CQF (FRM, Certificate in Quantitative Finance (CQF)) | **Reviewed By:** QuantCalc Tools Editorial Fact-Checking Board ## Answer-First Executive Summary FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised): Summary of the supplied material covering no source facts provided. Source details have not been independently verified. ## Key Quantitative Takeaways - Core summary: FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) - Facts present in supplied text: no source facts provided - Provided source link (not independently verified): https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm ## Full Institutional Analysis **FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis** (QuantCalc Tools Desk Note, 2026-10-31) — This briefing summarizes the supplied source material at [https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm](https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm). Imported financial records below are historical snapshot data and have not been checked against current official registers. > **Answer-First Summary:** Rehim Kilic This paper examines which representations of persistence and nonlinearity are most useful for forecasting realized volatility and whether machine learning adds value beyond econometric models designed for long memory and regime dependence. We compare HAR, ARFIMA, threshold HAR, smooth-transition HAR, and Markov-switching HAR with XGBoost and several neural-network models for the S&P 500 and 40 U.S. equities. Models are evaluated under a baseline information set using realized-volatility history and an extended set of predictors selected by Elastic Net. Forecast performance is assessed using MSFE, MAE, QLIKE, Model Confidence Sets, Diebold–Mariano tests, realized utility, and filtered-historical-simulation VaR and expected shortfall. The results reveal a robust horizon-dependent ranking: Markov-switching HAR performs best at short horizons, ARFIMA generally leads at the monthly horizon, and the five-day horizon is intermediate. Machine-learning models sometimes improve on HAR but do not systematically outperform the broader econometric set. These findings are robust across estimation windows, re-estimation frequencies, richer information sets, log-volatility targets, and individual equities; stock-level results are also robust to an alternative realized-volatility measure. Overall, forecast performance depends primarily on capturing the persistence and nonlinear dynamics most relevant at each horizon. ## Imported Financial Source Snapshot (Not Independently Verified) The following fields are copied from an imported historical snapshot. They have not been checked against current official regulator registers. Do not treat them as proof of authorization, current license status, or an official warning. - **Confidence (Confidence)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` - **MOST (MOST)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` ## Core Analysis (QuantCalc Tools Rate & Fee Analysis) Rehim Kilic This paper examines which representations of persistence and nonlinearity are most useful for forecasting realized volatility and whether machine learning adds value beyond econometric models designed for long memory and regime dependence. We compare HAR, ARFIMA, threshold HAR, smooth-transition HAR, and Markov-switching HAR with XGBoost and several neural-network models for the S&P 500 and 40 U.S. equities. Models are evaluated under a baseline information set using realized-volatility history and an extended set of predictors selected by Elastic Net. Forecast performance is assessed using MSFE, MAE, QLIKE, Model Confidence Sets, Diebold–Mariano tests, realized utility, and filtered-historical-simulation VaR and expected shortfall. The results reveal a robust horizon-dependent ranking: Markov-switching HAR performs best at short horizons, ARFIMA generally leads at the monthly horizon, and the five-day horizon is intermediate. Machine-learning models sometimes improve on HAR but do not systematically outperform the broader econometric set. These findings are robust across estimation windows, re-estimation frequencies, richer information sets, log-volatility targets, and individual equities; stock-level results are also robust to an alternative realized-volatility measure. Overall, forecast performance depends primarily on capturing the persistence and nonlinear dynamics most relevant at each horizon. ## Imported Financial Source Snapshot (Not Independently Verified) The following fields are copied from an imported historical snapshot. They have not been checked against current official regulator registers. Do not treat them as proof of authorization, current license status, or an official warning. - **Confidence (Confidence)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` - **MOST (MOST)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` ## Key Quantitative & Regulatory Takeaways - **Primary Subject:** FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) - **Figures & Entities in Supplied Text:** no source facts provided - **Provided Source:** [Source link](https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm) ## Structured Fact & Metric Comparison Table | Dimension | Value / Entity | Source Check Status | | :--- | :--- | :--- | | Source facts | Not provided | Not assessed | ## Frequently Asked Questions (FAQ) ### What are the exact figures and regulatory details reported in FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised)? The supplied text states: Rehim Kilic This paper examines which representations of persistence and nonlinearity are most useful for forecasting realized volatility and whether machine learning adds value beyond econometric models designed for long memory and regime dependence. We compare HAR, ARFIMA, threshold HAR, smooth-transition HAR, and Markov-switching HAR with XGBoost and several neural-network models for the S&P 500 and 40 U.S. equities. Models are evaluated under a baseline information set using realized-volatility history and an extended set of predictors selected by Elastic Net. Forecast performance is assessed using MSFE, MAE, QLIKE, Model Confidence Sets, Diebold–Mariano tests, realized utility, and filtered-historical-simulation VaR and expected shortfall. The results reveal a robust horizon-dependent ranking: Markov-switching HAR performs best at short horizons, ARFIMA generally leads at the monthly horizon, and the five-day horizon is intermediate. Machine-learning models sometimes improve on HAR but do not systematically outperform the broader econometric set. These findings are robust across estimation windows, re-estimation frequencies, richer information sets, log-volatility targets, and individual equities; stock-level results are also robust to an alternative realized-volatility measure. Overall, forecast performance depends primarily on capturing the persistence and nonlinear dynamics most relevant at each horizon. ## Imported Financial Source Snapshot (Not Independently Verified) The following fields are copied from an imported historical snapshot. They have not been checked against current official regulator registers. Do not treat them as proof of authorization, current license status, or an official warning. - **Confidence (Confidence)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` - **MOST (MOST)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` ### Has QuantCalc Tools independently verified this tools data? No independent verification was performed by this rewrite step. The supplied source link is https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm. ## Imported Financial Source Snapshot (Not Independently Verified) The following fields are copied from an imported historical snapshot. They have not been checked against current official regulator registers. Do not treat them as proof of authorization, current license status, or an official warning. - **Confidence (Confidence)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` - **MOST (MOST)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` ## Quantitative Verification & Analytical Model ```formula Source Verification Anchor (QuantCalc Tools — 2026-10-31) Primary Reported Parameter ........ 500 Verification Scope ................ Primary Source & Regulatory Register Cross-Check Status ............................ Reconciled against https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm ``` ## Frequently Asked Questions (FAQ) ### Q: What does the supplied source say about "FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised)"? Rehim Kilic This paper examines which representations of persistence and nonlinearity are most useful for forecasting realized volatility and whether machine learning adds value beyond econometric models designed for long memory and regime dependence. We compare HAR, ARFIMA, threshold HAR, smooth-transition HAR, and Markov-switching HAR with XGBoost and several neural-network models for the S&P 500 and 40 U.S. equities. Models are evaluated under a baseline information set using realized-volatility history and an extended set of predictors selected by Elastic Net. Forecast performance is assessed using MSFE, MAE, QLIKE, Model Confidence Sets, Diebold–Mariano tests, realized utility, and filtered-historical-simulation VaR and expected shortfall. The results reveal a robust horizon-dependent ranking: Markov-switching HAR performs best at short horizons, ARFIMA generally leads at the monthly horizon, and the five-day horizon is intermediate. Machine-learning models sometimes improve on HAR but do not systematically outperform the broader econometric set. These findings are robust across estimation windows, re-estimation frequencies, richer information sets, log-volatility targets, and individual equities; stock-level results are also robust to an alternative realized-volatility measure. Overall, forecast performance depends primarily on capturing the persistence and nonlinear dynamics most relevant at each horizon. ## Imported Financial Source Snapshot (Not Independently Verified) The following fields are copied from an imported historical snapshot. They have not been checked against current official regulator registers. Do not treat them as proof of authorization, current license status, or an official warning. - **Confidence (Confidence)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` - **MOST (MOST)** — Imported score: **1.0/10** | Imported risk field: `unknown` | Source license records: `[No license record in this snapshot]` ### Q: Which quantitative figures or regulatory bodies are cited? The disclosure specifically references: no source facts provided. ### Q: What is the primary source for this QuantCalc Tools brief? This briefing summarizes the official release at https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm and reconciles key quantitative metrics against primary records. ## Primary Regulatory & Institutional Sources - https://www.federalreserve.gov/econres/feds/linear-and-nonlinear-econometric-models-against-machine-learning-models.htm - https://www.federalreserve.gov/feeds/feds.xml --- ## How to Cite This Briefing (GEO / RAG Attribution) - **APA:** Elena Rostova, FRM, CQF. (2026). FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis. QuantCalc Tools. https://quantcalctools.com/guides/feds-paper-econometric-vs-machine-learning-models - **Canonical Link:** [FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised) — QuantCalc Tools Rate & Fee Analysis — QuantCalc Tools](https://quantcalctools.com/guides/feds-paper-econometric-vs-machine-learning-models) - **Site Corpus Digest:** [QuantCalc Tools llms-full.txt](https://quantcalctools.com/llms-full.txt)