Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Unsupervised ML and fraud detection with deep neural networks

Giorgia Fortuna (Machine Learning Reply)
16:00–16:40 Wednesday, 10 October 2018
AI in the Enterprise, Impact of AI on Business and Society
Location: Hilton Meeting Room 3-6
Secondary topics:  Computer Vision, Financial Services

Who is this presentation for?

  • Data scientists and AI researchers

Prerequisite knowledge

  • A basic understanding of deep learning and unsupervised machine learning (useful but not required)

What you'll learn

  • Explore state-of-the-art innovations in fraud detection
  • Learn how unsupervised ML fits into the picture

Description

Fraud detection is becoming one of the main focuses of modern AI algorithms. If you think of it as a corollary of anomaly detection and more generally of unsupervised machine learning, the AI world opens up to you with all of its new techniques, including convolutional and recurrent neural networks. Efficient face recognition and signature check enhance the possibility of successfully detecting fraudulent activities and can be applied in many contexts, such as finance end bank security. Computer vision and machine learning with deep convolutional neural networks have been used to identify and verify face images working on features extracted through a data preprocessing phase.

Giorgia Fortuna explores state-of-the-art innovations in fraud detection and explains how unsupervised ML fits into the picture, focusing on signature checks and face recognition. You’ll learn how to tackle the signature check problem using deep convolutional neural networks in a way similar to face recognition. Along the way, Giorgia offers an overview of feature extraction before diving deeper into Siamese networks and how they can be used for this task as well as how to boost the performance of these networks by introducing probabilistic unsupervised machine learning algorithms in order to approach the problem from the prospective of anomaly detection.

Photo of Giorgia Fortuna

Giorgia Fortuna

Machine Learning Reply

Giorgia Fortuna is a software developer and machine learning consultant at Machine Learning Reply, where she develops and supervises all kinds of ML projects, from building topic detectors and conversational agents to developing forecasting models. Previously, Giorgia focused on generative and unsupervised ML from a more theoretical point of view before moving to real-world cases and applications. Her background is in pure mathematics, giving her the ability to analyze and capture what is important and valuable when talking about innovation and helping her address commercial needs with machine learning technology to build intelligent systems that exploit data to increase business value.