MLOps.community Hard Learned Lessons from Over a Decade in AI
40 snips
Jun 6, 2025 Mike Del Balso, CEO and co-founder of Tecton, shares his decade-long journey in AI innovation, including the creation of Uber's Michelangelo ML platform. He discusses the evolution of predictive machine learning use cases, emphasizing the significance of feature stores. Del Balso explores the challenges of real-time data utilization, fraud detection, and the importance of model maturity in business impact. He also highlights the relevance of integrating generative AI with ML for enhanced marketing efficiency, turning complex data into smarter decisions.
AI Snips
Chapters
Transcript
Episode notes
Uber's ML Journey and Feature Store
- Mike Del Balso shared his experience leading Uber's Michelangelo ML platform where a major blocker was data pipelines.
- They built a feature store to automate and centralize data pipelines enabling scalable real-time ML projects.
Core ML Use Cases Defined
- Core ML use cases that generate significant value include customer acquisition, risk estimation, fraud detection, and operational efficiency.
- Every one of these decision areas requires high accuracy, speed, and reliability to impact business performance.
Boost ML Delivery Velocity
- Accelerate ML delivery by increasing team velocity and enabling faster iteration cycles.
- Improving feature quality and blending diverse data sources also boosts model accuracy and decision effectiveness.