Anomaly Detection - Using machine learning to indentify ununsual patterns in data - Richard Thomas, PWC & Anastasia Varlet, PWC

May 16, 2019, 13:50 - 14:20

Machine learning is currently disrupting the way companies are interacting with their data and adjusting their processes. Anomaly detection is a technique enabling the identification of unusual patterns or behaviors that do not conform to the expected outcome from the data model. Such outliers can reveal rare events and simple deviations, but also process weaknesses, errors or even fraud. As such, anomaly detection is a key technology that Internal Audit can leverage to gain new insights and drastically accelerate its work. In this talk, we will present a machine learning-based anomaly detection framework that can be used to review a company’s processes, reveal weaknesses in controls as well as monitor the quality of their data.