Uncertainty on Asynchronous Time Event Prediction
This work addresses uncertainty in event prediction for applications in various industries, representing an incremental improvement with novel method combinations.
The paper tackled predicting the next event in asynchronous sequences and how predictions change over time, introducing WGP-LN and FD-Dir architectures that model distribution evolution with logistic normal and Dirichlet distributions, achieving high performance in experiments on class prediction, time prediction, and anomaly detection across various datasets.
Asynchronous event sequences are the basis of many applications throughout different industries. In this work, we tackle the task of predicting the next event (given a history), and how this prediction changes with the passage of time. Since at some time points (e.g. predictions far into the future) we might not be able to predict anything with confidence, capturing uncertainty in the predictions is crucial. We present two new architectures, WGP-LN and FD-Dir, modelling the evolution of the distribution on the probability simplex with time-dependent logistic normal and Dirichlet distributions. In both cases, the combination of RNNs with either Gaussian process or function decomposition allows to express rich temporal evolution of the distribution parameters, and naturally captures uncertainty. Experiments on class prediction, time prediction and anomaly detection demonstrate the high performances of our models on various datasets compared to other approaches.