STOCKHOLM, SWEDEN - Logical Clocks introduces a new machine learning technique to train models for fraud detection using deep learning and Generative Adversarial Networks (GANs). The technique, available on Hopsworks, the world’s first data platform with a Feature Store, helped Swedbank, the oldest and largest bank in Sweden, reduce costs associated with fighting fraud.
Fraud is a major challenge across the globe. The estimated aggregate lost turnover for companies, governments and individuals as a result of financial crimes is valued at €40 trillion, according to a report revealing the true cost of financial crime. Although there are no public numbers on the cost of financial crime in Sweden, it is estimated by local governmental organisations that the amount being laundered each year amounts to billions.
Leading financial institutions are now investing large amounts of resources in machine learning (ML) to detect and prevent fraud. However, a major challenge in applying ML for fraud detection are the constant changes such as new money transfer schemes being introduced into the market, countries joining and leaving common payment areas or currencies, and new money laundering schemes frequently appearing.
To overcome these challenges and quickly update machine learning models, Logical Clocks offers a new approach to train models for fraud detection using a semi-supervised deep learning technique known as GANs.
"GANs are now the state-of-the-art approach to combating fraud and anti-money laundering because they can overcome the class imbalance problem. That is, there are lots of examples of non-fraudulent transactions, but few examples of fraudulent transactions”, comments Dr. Jim Dowling, CEO at Logical Clocks and Associate Professor at KTH Royal Institute of Technology in Sweden.
Swedbank deployed Hopsworks technology to increase the detection rate and reduce costs of transactions associated with fraud. The bank previously employed a traditional ML rule-based system that generated 99 false-positives (alerts where the transaction did not involve fraud) for every 100 alerts. This increases the time and costs to process the data since every positive flag requires a manual investigation. After deploying Hopsworks’ GANs technique, Swedbank was able to reduce this to only 1 false-positive for every 2 alerts.
“The benefits go beyond just cost savings. The new approach makes it harder for fraudsters to avoid detection. They will no longer be able to make small adjustments in how they launder their money to get around a relatively static set of rules”, concludes Dowling.
For further information and interviews, please contact:
PR & Communications Manager
Logical Clocks was founded by the team that created and continues to drive Hopsworks, a full-stack data-intensive platform for AI. With offices in Stockholm, London and Palo Alto, Logical Clocks aims to simplify the process of refining data into intelligence at scale.
Mikael Ronström joins Logical Clocks as Head of Data. Mikael Ronström is the inventor and lead developer of NDB Cluster, an open-source distributed database underlying the MySQL Cluster platform.
Logical Clocks, the data company behind the world’s first Enterprise Feature Store for Machine Learning, today announced full support for Microsoft Azure on its cloud managed data platform, Hopsworks. The announcement complements the existing support for Amazon Web Service (AWS), thus enterprises can now manage features for training and serving models at scale on Hopsworks while maintaining control of their data inside their organisation’s accounts on the most popular cloud platforms.
Logical Clocks introduces a new machine learning technique to train models for fraud detection using deep learning and Generative Adversarial Networks (GANs). The technique, available on Hopsworks, the world’s first data platform with a Feature Store, helped Swedbank, the oldest and largest bank in Sweden, reduce costs associated with fighting fraud.
Logical Clocks announced it is developing the first enterprise Feature Store for Edge Computing for the AI-NET ANIARA project, part of the CELTIC-NEXT programme, to bring artificial intelligence to 5G networks in Europe. To meet infrastructural requirements on performance, security, reliability and scalability, the project will take advantage of Logical Clocks’ Feature Store.
Logical Clocks, the enterprise behind Hopsworks - the first data platform for designing and operating machine learning and artificial intelligence (AI) applications at scale with a Feature Store - announces the launch of Hopsworks.ai, the world’s first managed cloud platform for AI with a feature store.
On September 5th, 2019, Logical Clocks won the European DatSci award for “Data Science Technology Innovation of the Year”. Hopsworks is a data-intensive platform for data science and AI, that includes the first Enterprise Feature Store for Machine Learning.
Hopsworks 0.10 brings the latest features, improvements and bug fixes. It is the biggest release done so far, made up of 191 JIRAs including many new features. Also, this version marks the last of the 0.x series, as Hopsworks is gearing up towards its 1.x series starting with 1.0 end of Q3 2019.
Hopsworks 0.9.0 brings the latest features, improvements and bug fixes. It introduces Apache Airflow as-a-service which means users can now create their own workflows from within their familiar environment of a Hopsworks project. You can get started with Airflow in Hopsworks by visiting the user-guide.
Announcing the release of the first Enterprise Feature Store for Machine Learning. The Feature Store solves the problem of ad-hoc and siloed machine learning pipelines, where features, the training data for such pipelines, tend to become disorganized, disjointed, and duplicated, leading to correctness problems and redundant work.
Hopsworks 0.8.0 brings the latest features, improvements and bug fixes. It comes a short while after version 0.7.0 and brings the world’s first open-source feature store, a revamped REST API for managing jobs in Hopsworks and improvements in visualization for python notebooks.