Episode 98: Building Trust in AI Through Model Interpretability
About this episode
This episode discusses the importance of model interpretability in AI to build trust among stakeholders in high-stakes environments.
When your machine learning model makes a decision that affects someone's medical treatment, financial security, or legal rights, "the algorithm said so" isn't good enough. Stakeholders need to understand why models make the decisions they do, and in high-stakes environments, model interpretability becomes the difference between AI adoption and AI rejection. In this episode, Serg Masis joins Dr. Genevieve Hayes to share practical strategies for building interpretable machine learning models that earn stakeholder trust and accelerate AI adoption within your organisation. You'll learn: The crucial distinction between interpretable and explainable models [07:06] Why feature engineering matters more than algorithm choice [14:56] How to use models to improve your data quality [17:59] The underrated technique that builds stakeholder trust [21:20] Guest Bio Serg Masis is the Principal AI Scientist at Syngenta, a leading agricultural company with a mission to improve global food security. He is also the author of Interpretable Machine Learning with Python and co-author of the upcoming DIY AI and Building Responsible AI with Python . Links Serg's Website Connect with Serg on LinkedIn…
More episodes of Value Driven Data Science
- Episode 102: [Value Boost] How Giving Away Your Work for Free Can Build Your Authority as a Data Scientist
- Episode 101: Why Traditional Statistics Still Matters in the Age of AI
- Episode 100: What Data Science Value Really Means
- Episode 99: [Value Boost] Preventing ML Bias Before it Becomes a Problem
- Episode 97: [Value Boost] Mathematical Modelling as a Gateway to ML Success
- Episode 96: Making Better Decisions with ML and Optimisation
Explore listener stats, chart rankings, contacts and more on the Value Driven Data Science podcast page.