Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140971601> ?p ?o ?g. }
- W3140971601 abstract "Abstract We inspect how accurate machine learning (ML) is at forecasting realized variance of the Dow Jones Industrial Average index constituents. We compare several ML algorithms, including regularization, regression trees, and neural networks, to multiple heterogeneous autoregressive (HAR) models. ML is implemented with minimal hyperparameter tuning. In spite of this, ML is competitive and beats the HAR lineage, even when the only predictors are the daily, weekly, and monthly lags of realized variance. The forecast gains are more pronounced at longer horizons. We attribute this to higher persistence in the ML models, which helps to approximate the long memory of realized variance. ML also excels at locating incremental information about future volatility from additional predictors. Lastly, we propose an ML measure of variable importance based on accumulated local effects. This shows that while there is agreement about the most important predictors, there is disagreement on their ranking, helping to reconcile our results." @default.
- W3140971601 created "2021-04-13" @default.
- W3140971601 creator A5008840813 @default.
- W3140971601 creator A5011001301 @default.
- W3140971601 creator A5061167387 @default.
- W3140971601 date "2022-06-30" @default.
- W3140971601 modified "2023-09-30" @default.
- W3140971601 title "A Machine Learning Approach to Volatility Forecasting" @default.
- W3140971601 cites W1594842258 @default.
- W3140971601 cites W1678356000 @default.
- W3140971601 cites W1823577794 @default.
- W3140971601 cites W1963787328 @default.
- W3140971601 cites W1964864228 @default.
- W3140971601 cites W1977970167 @default.
- W3140971601 cites W1979575715 @default.
- W3140971601 cites W1988790447 @default.
- W3140971601 cites W1999996900 @default.
- W3140971601 cites W2000303290 @default.
- W3140971601 cites W2020925091 @default.
- W3140971601 cites W2035942174 @default.
- W3140971601 cites W2045746104 @default.
- W3140971601 cites W2066815740 @default.
- W3140971601 cites W2068138154 @default.
- W3140971601 cites W2070516830 @default.
- W3140971601 cites W2070534370 @default.
- W3140971601 cites W2082961314 @default.
- W3140971601 cites W2103496339 @default.
- W3140971601 cites W2117447427 @default.
- W3140971601 cites W2122825543 @default.
- W3140971601 cites W2125536334 @default.
- W3140971601 cites W2140585983 @default.
- W3140971601 cites W2144031751 @default.
- W3140971601 cites W2146134639 @default.
- W3140971601 cites W2155419203 @default.
- W3140971601 cites W2158595111 @default.
- W3140971601 cites W2499063677 @default.
- W3140971601 cites W2507684129 @default.
- W3140971601 cites W2745672448 @default.
- W3140971601 cites W2853380097 @default.
- W3140971601 cites W2895960091 @default.
- W3140971601 cites W2911964244 @default.
- W3140971601 cites W2954294000 @default.
- W3140971601 cites W2967187896 @default.
- W3140971601 cites W3004732066 @default.
- W3140971601 cites W3022041122 @default.
- W3140971601 cites W3035517615 @default.
- W3140971601 cites W3121532596 @default.
- W3140971601 cites W3122046970 @default.
- W3140971601 cites W3122131431 @default.
- W3140971601 cites W3122175640 @default.
- W3140971601 cites W3124028486 @default.
- W3140971601 cites W3125987794 @default.
- W3140971601 cites W3126064560 @default.
- W3140971601 cites W3126081245 @default.
- W3140971601 cites W4205539948 @default.
- W3140971601 cites W4212883601 @default.
- W3140971601 cites W4234698323 @default.
- W3140971601 cites W4241653265 @default.
- W3140971601 cites W4244967830 @default.
- W3140971601 cites W4251828876 @default.
- W3140971601 doi "https://doi.org/10.1093/jjfinec/nbac020" @default.
- W3140971601 hasPublicationYear "2022" @default.
- W3140971601 type Work @default.
- W3140971601 sameAs 3140971601 @default.
- W3140971601 citedByCount "6" @default.
- W3140971601 countsByYear W31409716012022 @default.
- W3140971601 countsByYear W31409716012023 @default.
- W3140971601 crossrefType "journal-article" @default.
- W3140971601 hasAuthorship W3140971601A5008840813 @default.
- W3140971601 hasAuthorship W3140971601A5011001301 @default.
- W3140971601 hasAuthorship W3140971601A5061167387 @default.
- W3140971601 hasBestOaLocation W31409716012 @default.
- W3140971601 hasConcept C105795698 @default.
- W3140971601 hasConcept C119857082 @default.
- W3140971601 hasConcept C121955636 @default.
- W3140971601 hasConcept C149782125 @default.
- W3140971601 hasConcept C154945302 @default.
- W3140971601 hasConcept C159877910 @default.
- W3140971601 hasConcept C162324750 @default.
- W3140971601 hasConcept C196083921 @default.
- W3140971601 hasConcept C2776135515 @default.
- W3140971601 hasConcept C33923547 @default.
- W3140971601 hasConcept C41008148 @default.
- W3140971601 hasConcept C50644808 @default.
- W3140971601 hasConcept C60092789 @default.
- W3140971601 hasConcept C83546350 @default.
- W3140971601 hasConcept C8642999 @default.
- W3140971601 hasConcept C91602232 @default.
- W3140971601 hasConceptScore W3140971601C105795698 @default.
- W3140971601 hasConceptScore W3140971601C119857082 @default.
- W3140971601 hasConceptScore W3140971601C121955636 @default.
- W3140971601 hasConceptScore W3140971601C149782125 @default.
- W3140971601 hasConceptScore W3140971601C154945302 @default.
- W3140971601 hasConceptScore W3140971601C159877910 @default.
- W3140971601 hasConceptScore W3140971601C162324750 @default.
- W3140971601 hasConceptScore W3140971601C196083921 @default.
- W3140971601 hasConceptScore W3140971601C2776135515 @default.
- W3140971601 hasConceptScore W3140971601C33923547 @default.
- W3140971601 hasConceptScore W3140971601C41008148 @default.
- W3140971601 hasConceptScore W3140971601C50644808 @default.