Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification

TL;DR

This paper explores probabilistic models for novelty detection, focusing on mixed-type and sequence data, proposing new methods that improve accuracy, interpretability, scalability, and robustness in anomaly identification tasks.

Contribution

It introduces a probabilistic nonparametric approach using Dirichlet process mixtures and deep Gaussian process autoencoders for enhanced novelty detection.

Findings

Probabilistic nonparametric method outperforms traditional techniques on mixed data.

Autoencoder-based model with deep Gaussian processes improves sequence anomaly detection.

Comprehensive comparison of novelty detection methods across data types.

Abstract

Novelty detection is the unsupervised problem of identifying anomalies in test data which significantly differ from the training set. Novelty detection is one of the classic challenges in Machine Learning and a core component of several research areas such as fraud detection, intrusion detection, medical diagnosis, data cleaning, and fault prevention. While numerous algorithms were designed to address this problem, most methods are only suitable to model continuous numerical data. Tackling datasets composed of mixed-type features, such as numerical and categorical data, or temporal datasets describing discrete event sequences is a challenging task. In addition to the supported data types, the key criteria for efficient novelty detection methods are the ability to accurately dissociate novelties from nominal samples, the interpretability, the scalability and the robustness to anomalies located in the training data. In this thesis, we investigate novel ways to tackle these issues. In particular, we propose (i) an experimental comparison of novelty detection methods for mixed-type data (ii) an experimental comparison of novelty detection methods for sequence data, (iii) a probabilistic nonparametric novelty detection method for mixed-type data based on Dirichlet process mixtures and exponential-family distributions and (iv) an autoencoder-based novelty detection model with encoder/decoder modelled as deep Gaussian processes.