![Episode 95: [Value Boost] Building Models That Work While Millions Are Watching](https://img.transistorcdn.com/pZTzGpglmo9iMB27fnVmhpRYDC4wkM6iXXPR3SIbu44/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS80YzU3/MWI0ZjdlNDA1OTYz/ZGE1OWEyYTEyODk4/NDQ2NC5qcGc.jpg)
Episode 95: [Value Boost] Building Models That Work While Millions Are Watching
From Value Driven Data Science by Dr Genevieve Hayes
February 25, 2026 · 12 min · Episode 95
About this episode
The episode discusses the challenges of building effective models in high-pressure situations, specifically during the Cricket World Cup.
Building a model for an academic paper is one thing. Building a model that has to work perfectly during the Cricket World Cup with millions watching is something else entirely. There's no room for the kind of errors that might be acceptable in research settings or even standard business applications. In this Value Boost episode, Prof. Steve Stern joins Dr. Genevieve Hayes to share practical lessons from deploying the Duckworth-Lewis-Stern method in high-pressure, real-time environments where mistakes have global consequences. You'll learn: Why model simplicity matters more than you think [02:04] The two types of errors you need to understand [03:21] How to test models for extreme situations [05:50] The balance between confidence and humility [07:37] Guest Bio Prof. Steve Stern is a Professor of Data Science at Bond University, and is the official custodian of the Duckworth-Lewis-Stern (DLS) cricket scoring system. Links Contact Steve at Bond University Connect with Genevieve on LinkedIn Be among the first to hear about the release of each new podcast episode by signing up HERE
People in this episode
Host: Dr Genevieve Hayes
Guest: Prof. Steve Stern
Topics covered
- model building
- data science
- real-time environments
- sports analytics
- error management
Keywords
- model simplicity
- Duckworth-Lewis-Stern
- data science
- real-time modeling
- error types
Mentioned in this episode
Organizations: Bond University
Books & works: Duckworth-Lewis-Stern method
More episodes of Value Driven Data Science
- Episode 109: How to Measure Anything and Make Better Decisions · June 10, 2026 · 30 min
- Episode 108: [Value Boost] How to Use AI Without Losing Your Edge · June 3, 2026 · 10 min
- Episode 107: Building a Virtual Empire of AI Specialists · May 27, 2026 · 29 min
- Episode 106: [Value Boost] When AI Isn't the Answer · May 20, 2026 · 12 min
- Episode 105: From AI Idea to Production Reality · May 13, 2026 · 29 min
- Episode 104: [Value Boost] The Four Zones of AI Productivity for Data Scientists · May 6, 2026 · 14 min
Explore listener stats, chart rankings, contacts and more on the Value Driven Data Science podcast page.