Patrik Masec

Patrik is Data Science Team Lead at the leading Croatian fintech company Aircash. In this role, he established the Data Science department based on a series of successfully managed and completed projects in artificial intelligence and advanced analytics, in collaboration with other departments (IT, Sales, Compliance, Customer Support, Risk). Examples of successful projects in production include face recognition and liveness detection, personal document data extraction, multilingual digit recognition, and user segmentation. These projects have reduced fraudulent account takeovers, accelerated customer support, reduced new user onboarding time, decreased costs and required resources for user verification, and enabled the targeted acquisition of new users. Throughout his studies at the Faculty of Electrical Engineering and Computing in Croatia, Patrik founded a strength training optimization application for Android called SmartLift AI. He also participated in machine learning competitions on Kaggle and achieved remarkable results.

How to Build an In-House Automated Video Verification System

Remote onboarding and video verification of new users have become hot topics in recent times. In this lecture, we’ll explore the development of an automated and robust in-house video verification system, focusing on various required AI models. We will cover several models in the domains of computer vision and speech recognition, such as face detection and recognition, face liveness detection, document detection and recognition, document parsing, and multilingual number speech recognition.