Détermination d’un ensemble d’attributs à partir des données d’opération des clients en vue d’en faire le classement

Verafin est une entreprise du secteur de la technologie de l’information qui se spécialise dans les solutions de renseignements sur la clientèle pour les établissements financiers de petite et moyenne taille. Il existe une forte demande pour les systèmes automatiques de détection et de prévention des fraudes et du blanchiment d'argent puisque ces activités coûtent […]

Read More
Segmentation des clients en fonction de données sur les transactions

Les systèmes automatisés de détection et de prévention des fraudes et du blanchiment sont en forte demande parce que ces activités criminelles coûtent chaque année des millions de dollars au secteur financier. Un des problèmes clés des techniques de détection est le profilage descriptif exact des comptes. Il convient donc de cerner les caractéristiques saillantes […]

Read More
Interpretable dimensionality reduction of multivariate time series data using LSTM based autoencoders

Data collection over time is a common practice in many large organizations- including financial institutions and health care providers- often with the goal of using this data to predict future challenges and opportunities. While this data may contain valuable information, it is often unstructured, coming from different sources and recorded at different times. This lack […]

Read More
Hunt for the Super-Spreaders — A Complex Networks Approach

Contagious diseases, such as SARS and COVID-19, bring a large amount of damage to human’s life and world economy. Pathogens spread among individuals through the contact network. It is observed that most social networks show a power-law degree distribution, implying that hubs exist in these networks. Finding underlying super-spreaders (hubs) and isolating or immunizing them […]

Read More
Enhanced Graph Convolutional Networks using Local Structural Information

Over the past few years, Graph Convolutional Networks (GCNs) have achieved state-of-the-art performance in machine learning tasks on graph data and have been widely applied to many real-world applications across different fields, such as traffic prediction, user behavior analysis, and fraud detection. However, networks in the real world are often with heterogeneous degree distributions, such […]

Read More
Development of an improved generative adversarial network method for data augmentation and its application in environmental and financial domains

Using simplified language understandable to a layperson; provide a general, one-paragraph description of the proposed research project to be undertaken by the intern(s) as well as the expected benefit to the partner organization. (100 – 150 words) This project aims to increase image datasets by not doing experiments or collecting physical checks. Instead, the image […]

Read More
Feature Set Generation from Customer Transaction Data for Customer Classification

Verafin is an information technology company that specializes in customer intelligence solutions for small and midsize financial institutions. There is a high demand for automated fraud and money laundering detection and prevention systems since such activities cost millions to the financial industry every year. A key problem with detection techniques is the accurate and descriptive […]

Read More
Customer Segmentation Using Feature Set Generated from Customer Transaction Data

There is a high demand for automated fraud and money laundering detection and prevention systems since such activities costs millions to the financial industry every year. A key problem in detection techniques is the accurate and descriptive profiling of the accounts. Thus, it is important to identify the salient features in traction data that would […]

Read More
Deep Fraud Detection

Financial fraud is a serious issue that is taking place globally and causing considerable damage at great expense. Statistical analysis and machine learning tools can help financial institutions detect different types of fraud. In some cases however, mislabeling and the cost of classification may actually increase the volume of ‘false positives’ for supervised methods. As […]

Read More