Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization
This addresses forecasting challenges in high-dimensional functional data for fields like finance or climate science, offering an explainable alternative to black-box deep learning, though it is incremental as it builds on existing factor models and kernels.
The paper tackles forecasting high-dimensional functional time series by introducing the Deep Functional Factor Model (DF2M), a Bayesian nonparametric model that uses deep kernels and variational inference, achieving superior predictive accuracy and better explainability compared to conventional deep learning models on four real-world datasets.
This paper introduces the Deep Functional Factor Model (DF2M), a Bayesian nonparametric model designed for analysis of high-dimensional functional time series. DF2M is built upon the Indian Buffet Process and the multi-task Gaussian Process, incorporating a deep kernel function that captures non-Markovian and nonlinear temporal dynamics. Unlike many black-box deep learning models, DF2M offers an explainable approach to utilizing neural networks by constructing a factor model and integrating deep neural networks within the kernel function. Additionally, we develop a computationally efficient variational inference algorithm to infer DF2M. Empirical results from four real-world datasets demonstrate that DF2M provides better explainability and superior predictive accuracy compared to conventional deep learning models for high-dimensional functional time series.