Giovanni Degiorgi is a forward-thinking Solution Architect at Swiss Post, based in Lugano, Switzerland. With a keen focus on digital transformation, Giovanni plays a crucial role in guiding the organization's transition to cloud technologies. His expertise in designing and implementing robust cloud solutions has been instrumental in driving innovation and efficiency within Swiss Post.
Giovanni recently enhanced his technical prowess by completing a Master's degree in Machine Learning and Artificial Intelligence from SUPSI (University of Applied Sciences and Arts of Southern Switzerland). This advanced education has equipped him with cutting-edge knowledge, allowing him to bridge the gap between traditional IT infrastructure and modern data-driven technologies.
In his current role, Giovanni is actively supporting the development team at Swiss Post in establishing foundational blueprints for cloud architecture. His efforts are particularly focused on implementing MLOps (Machine Learning Operations) practices using the AWS platform. This initiative aims to streamline the deployment, monitoring, and management of machine learning models in production environments.
Over the past years, criminal activities on the Swiss Post portal have amounted to approximately 5 million Swiss Francs per year . Criminal organizations and their activities have become increasingly sophisticated and organized over time, with cybercrime remaining a significant concern for online retailers and services.
In this presentation we address the challenges of fraud detection and imbalanced datasets, outlining the procedures implemented to manage data access at an enterprise level within Swiss Post. We present a machine learning approach to detect potential fraudulent addresses, preventing the activation of an account when risk is identified.
Our innovative strategy employs a contextual Multi-Armed Bandit (MAB) model, trained on shipment data and expert fraud evidence, to take actions that maximize rewards by minimizing potential fraud cases. This novel approach, leveraging artificial intelligence and modern reinforcement learning techniques, is fully hosted on a cloud platform, allowing for on-demand scaling based on specific time requirements.
We explore innovative machine learning approaches, including MLOps and our contextual MAB-based strategy, discussing their implementation and benefits. The empirical results, based on real-world data from Swiss Post logistic services, demonstrate that we can successfully identify a portion of the fraudulent addresses with the ability to improve our algorithm over time through expert feedback. These promising outcomes pave the way for future deployment in Swiss Post's production environment.
We delve into the integration of our solution within a large-scale enterprise setting, emphasizing the role of Continuous Integration and Continuous Deployment (CI/CD) pipelines in maintaining and improving the system.
Searching for speaker images...