Results 191 to 200 of about 5,695,240 (285)

The Accuracy Smoothness Dilemma in Prediction: A Novel Multivariate M‐SSA Forecast Approach

open access: yesJournal of Time Series Analysis, EarlyView.
ABSTRACT Forecasting presents a complex estimation challenge, as it involves balancing multiple, often conflicting, priorities and objectives. Conventional forecast optimization methods typically emphasize a single metric, such as minimizing the mean squared error (MSE), which may neglect other crucial aspects of predictive performance. To address this
Marc Wildi
wiley   +1 more source

Sparse Causal Dynamic Linear Regression

open access: yesJournal of Time Series Analysis, EarlyView.
ABSTRACT We develop a sparse causal dynamic regression framework for long multivariate time series. With very long time series, the potentially large number of lags and leads in a dynamic regression model often makes time‐domain estimation numerically unstable or intractable.
Rui Huang, Kung‐Sik Chan
wiley   +1 more source

Asymptotics of Time‐Varying Processes in Continuous‐Time Using Locally Stationary Approximations

open access: yesJournal of Time Series Analysis, EarlyView.
ABSTRACT We introduce a general theory on stationary approximations for locally stationary continuous‐time processes. Based on the stationary approximation, we use θ$$ \theta $$‐weak dependence to establish laws of large numbers and central limit type results under different observation schemes.
Robert Stelzer, Bennet Ströh
wiley   +1 more source

Reinforcement Learning for Jump‐Diffusions, With Financial Applications

open access: yesMathematical Finance, EarlyView.
ABSTRACT We study continuous‐time reinforcement learning (RL) for stochastic control in which system dynamics are governed by jump‐diffusion processes. We formulate an entropy‐regularized exploratory control problem with stochastic policies to capture the exploration–exploitation balance essential for RL.
Xuefeng Gao, Lingfei Li, Xun Yu Zhou
wiley   +1 more source

Nowcasting Swiss GDP Growth From Public Lead Texts: Simple Methods Are Sufficient

open access: yesOxford Bulletin of Economics and Statistics, EarlyView.
ABSTRACT Public lead texts from Swiss newspapers contain most of the signal needed to nowcast Swiss GDP growth in real time. I build an indicator from daily topic‐specific sentiment and recession measures extracted from three Swiss newspapers and evaluate it in pseudo‐real time.
Marc Burri
wiley   +1 more source

Home - About - Disclaimer - Privacy