Advances in Time Series Forecasting and Applications in Finance

Time series forecasting is a cornerstone of quantitative finance. At the research frontier, forecasting plays a central role in many areas. Accurate forecasts of returns and risk premia are fundamental for asset pricing, which lies at the core of systematic trading strategies. In risk management, forecasting volatility, tail risk, and correlation dynamics is essential for managing leverage, position sizing, and capital allocation.This Research Topic invites contributions that address key challenges in time series forecasting for financial applications, such as the development of robust models that capture regime shifts, nonlinear dependencies, cross-asset spillover effects, the use of machine learning techniques to capture complex interactions among features, and the evaluation of forecasting uncertainty and multivariate forecasting, etc.Topics of interest include (but are not limited to):- deep learning forecasting architectures,- tree-based machine learning methods,- adaptive signal processing,- state space models,- hybrid models,- conformal prediction,- hierarchical Bayesian models,- explainable AI for time series. Topic editors: Yu Mu, Young Shin Aaron Kim Source: https://www.frontiersin.org/research-topics/74678/advances-in-time-series-forecasting-and-applications-in-finance