< Back to previous page

Project

Unsupervised Representation Learning and Health Insurance Anomaly Detection

One of the most important reasons behind the advances in machine learning is due to their increasingly powerful representation learning capabilities. The most well-known type of representation learning is a neural network, which is a powerful type of model that can automatically extract features out of input data. However, one has little control over the types of features that a neural network learns. This motivates research into learning representations that can capture prior knowledge, offer insight into the model and can improve the learning process.
In this work, a number of unsupervised representation learning methods are discussed to increase performance, tackle biases, improve diversity and explainability of machine learning models. Specifically, the problem of mode collapse and complete mode coverage in generative adversarial networks is tackled.
Additionally, we extend the restricted kernel machines framework to time-series data such that it can learn time-series features and predict unseen future values.
Finally, a novel representation learning technique in combination with other state-of-the-art methods are employed to create a system that can help health insurance experts detect anomalous profiles.

 

Date:1 Oct 2018 →  15 Mar 2024
Keywords:Fraud detection, Machine learning
Disciplines:Applied mathematics in specific fields, Computer architecture and networks, Distributed computing, Information sciences, Information systems, Programming languages, Scientific computing, Theoretical computer science, Visual computing, Other information and computing sciences, Modelling, Biological system engineering, Signal processing, Control systems, robotics and automation, Design theories and methods, Mechatronics and robotics, Computer theory
Project type:PhD project