Scalable Joint Models for Reliable Uncertainty-Aware Event Prediction

TL;DR

This paper introduces a scalable, flexible joint modeling approach using sparse Gaussian processes for reliable, uncertainty-aware event prediction from complex, irregularly sampled multivariate time series data, outperforming existing methods.

Contribution

The paper proposes a novel scalable joint model based on sparse Gaussian processes that handles non-Gaussian noise and large data, along with an optimal event prediction policy.

Findings

Significantly outperforms state-of-the-art techniques in event prediction.

Effectively models highly challenging data structures including non-Gaussian noise.

Provides a principled decision-making policy balancing delay and accuracy.

Abstract

Missing data and noisy observations pose significant challenges for reliably predicting events from irregularly sampled multivariate time series (longitudinal) data. Imputation methods, which are typically used for completing the data prior to event prediction, lack a principled mechanism to account for the uncertainty due to missingness. Alternatively, state-of-the-art joint modeling techniques can be used for jointly modeling the longitudinal and event data and compute event probabilities conditioned on the longitudinal observations. These approaches, however, make strong parametric assumptions and do not easily scale to multivariate signals with many observations. Our proposed approach consists of several key innovations. First, we develop a flexible and scalable joint model based upon sparse multiple-output Gaussian processes. Unlike state-of-the-art joint models, the proposed model can explain highly challenging structure including non-Gaussian noise while scaling to large data. Second, we derive an optimal policy for predicting events using the distribution of the event occurrence estimated by the joint model. The derived policy trades-off the cost of a delayed detection versus incorrect assessments and abstains from making decisions when the estimated event probability does not satisfy the derived confidence criteria. Experiments on a large dataset show that the proposed framework significantly outperforms state-of-the-art techniques in event prediction.