Multi-view Kernel PCA for Time series Forecasting

TL;DR

This paper introduces a multi-view Kernel PCA model for multivariate time series forecasting, leveraging Restricted Kernel Machines, with solutions ranging from kernel ridge regression to pre-image problems, evaluated on standard datasets.

Contribution

It presents a novel multi-view Kernel PCA approach for time series forecasting, integrating eigenvalue decomposition and kernel methods for improved prediction accuracy.

Findings

Effective on multiple datasets

Comparable or superior to existing models

Insights into kernel choice impacts

Abstract

In this paper, we propose a kernel principal component analysis model for multi-variate time series forecasting, where the training and prediction schemes are derived from the multi-view formulation of Restricted Kernel Machines. The training problem is simply an eigenvalue decomposition of the summation of two kernel matrices corresponding to the views of the input and output data. When a linear kernel is used for the output view, it is shown that the forecasting equation takes the form of kernel ridge regression. When that kernel is non-linear, a pre-image problem has to be solved to forecast a point in the input space. We evaluate the model on several standard time series datasets, perform ablation studies, benchmark with closely related models and discuss its results.