Showing 1 - 10 of 32
We study the asymptotic properties of the Adaptive LASSO (adaLASSO) in sparse, high-dimensional, linear time-series models. We assume that both the number of covariates in the model and the number of candidate variables can increase with the sample size (polynomially or geometrically). In other...
Persistent link: https://www.econbiz.de/10010505038
In this paper we survey the most recent advances in supervised machine learning and highdimensional models for time series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods we pay special attention to penalized regressions and ensemble of models. The...
Persistent link: https://www.econbiz.de/10012390030
Persistent link: https://www.econbiz.de/10014287800
This paper evaluates the economic gains associated with following a volatility timing strategy based on a multivariate model of realized volatility. To study this issue we build a high frequency database with the most actively traded Brazilian stocks. Comparing with traditional volatility...
Persistent link: https://www.econbiz.de/10010402112
In this paper we consider modeling and forecasting of large realized covariance matrices by penalized vector autoregressive models. We propose using Lasso-type estimators to reduce the dimensionality to a manageable one and provide strong theoretical performance guarantees on the forecast...
Persistent link: https://www.econbiz.de/10010433899
Persistent link: https://www.econbiz.de/10011585234
It is widely known that Google Trends has become one of the most popular free tools used by forecasters both in academics and in the private and public sectors. There are many papers, from several different fields, concluding that Google Trends improve forecasts' accuracy. However, what seems to...
Persistent link: https://www.econbiz.de/10012510318
Persistent link: https://www.econbiz.de/10015045177
We study the asymptotic properties of the Adaptive LASSO (adaLASSO) in sparse, high-dimensional, linear time-series models. We assume that both the number of covariates in the model and the number of candidate variables can increase with the sample size (polynomially orgeometrically). In other...
Persistent link: https://www.econbiz.de/10011807460
In this paper we survey the most recent advances in supervised machine learning and highdimensional models for time series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods we pay special attention to penalized regressions and ensemble of models. The...
Persistent link: https://www.econbiz.de/10012817069