AI-Powered Cloud Solution for Digitizing Lottery Retail
I led the development and deployment of a cloud-native lottery slip recognition system for Germany's largest lottery provider. The solution replaces expensive, bulky legacy scanner terminals with affordable camera-based Android tablets, using a hybrid approach of machine learning and traditional image processing to achieve >99% recognition accuracy, even from crumpled, dirty, or low-quality inputs. Since launch in early 2023, the system has processed over 40,000 slips monthly with zero reported issues over 20+ months in production.
The impact was transformative: the client activated 100+ new sales locations, including kiosks, bakeries, and rural points of sale that were previously inaccessible due to hardware costs. The serverless, event-driven architecture on GCP ensures real-time processing, automatic scaling, and maintenance-free operations.
This solution has been showcased at global lottery and AI conferences, including:
- World Lottery Summit, Paris, France (Oct 2024)
- European Lotteries AI Seminar, Warsaw, Poland (May 2024)
- World Lottery Summit, Vancouver, Canada (Oct 2022)
- adesso summIT, Belek, Turkey (Oct 2022)
I was responsible for this project as part of my role as "Head of Machine Learning & GenAI - Google Cloud" at adesso SE.