DataVisor, the leading fraud detection company with solutions powered by transformational AI technology, has announced that Dr. Ting-Fang Yen, its Director of Research, will be speaking at the upcoming O’Reilly Artificial Intelligence Conference taking place in San Jose from Sept. 9 to 12.
Her session, ‘Talking to the machines: Monitoring production machine learning systems,’ is targeted at data scientists and engineers that build or maintain production machine learning models and takes place from 11:55am–12:35pm on Thursday, Sept. 12 at Location: LL21 C/D.
Yen will describe the design and implementation of a real-time system to monitor production machine learning systems that discover detection anomalies, such as volume spikes caused by spurious false positives, as well as gradual concept drifts when the model is no longer able to capture the target concept.
Part of this approach borrows from signal processing techniques for time series decomposition. The time series can be used to represent a sequence of model decisions on different types of input data or the amount of deviation between consecutive model runs. By calculating cross-correlation among the identified anomalies, a person can facilitate root cause analysis of the model behavior. This work is a step toward automated deployment of machine learning in production as well as new tools for interpreting model inference results.
“What happens when labeled data is lacking In production machine learning systems? In many applications, labels are expensive to obtain or cannot be obtained in a timely manner. I will examine this in greater detail and highlight, in practical ways, how to overcome this challenge,” said Yen.
The annual O’Reilly Artificial Intelligence Conference provides delegates with detailed case studies, technical sessions, and training along with access to the leading minds in AI. The event is moreover a popular networking platform to engage with thousands of innovative researchers, data scientists, engineers, senior developers, and executives across industries.
“Today’s business environment requires that organizations use AI and machine learning in increasingly sophisticated ways. This necessitates a holistic approach to data analysis and leveraging solutions capable of proactively identifying known as well as unknown challenges. We live in a real-time world and having solutions on our side that are able to meet this requirement is a significant advantage,” she added.
Prior to DataVisor, Yen was principal research scientist at RSA Labs and threat scientist at E8 Security. She received her Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University, Pittsburgh, Pa.
Currently, her work focuses on network and information security data analysis. This sees her combining data science with security domain expertise to develop practical technologies and solutions. Her research has shaped product directions and has been published and presented at top industry and academic security conferences.
DataVisor is the leading fraud detection platform powered by transformational AI technology. Using proprietary unsupervised machine learning algorithms, DataVisor restores trust in digital commerce by enabling organizations to proactively detect and action fast-evolving fraud patterns, and prevent future attacks before they happen. Combining advanced analytics and an intelligence network of more than 4B global user accounts, DataVisor protects against financial and reputational damage across a variety of industries, including financial services, marketplaces, ecommerce, and social platforms.