Machine Learning in the Wild

« All happy families are alike; each unhappy family is unhappy in its own way. »

Tolstoy's opening line applies just as well to machine learning models. Successful ones all look the same: clean data, solid capture infrastructure, hard work, and enough stakeholder trust to hand over the reins in production. But every failed model fails in its own way - a training set that silently drifted, a feature that leaked the future, a business constraint no one flagged, a team overwhelmed by a model too complex for their scientific habits, or subtle context shifts once the system went live. No two headstones read the same.

After 20 years of building and deploying models in banking, insurance, e-commerce, and hedge funds, I have catalogued many of these failure modes firsthand. I trained in mathematics at École Polytechnique, co-founded a startup in Silicon Valley, consulted within McKinsey's Technology arm, and spent years managing data-heavy programs at Société Générale's Corporate and Investment Bank. In 2012, I founded ArsChitectura, a boutique consulting firm dedicated to machine learning and artificial intelligence for high-stakes industries.

Over those years, I have built and deployed predictive models and AI-driven systems across these sectors - from credit scoring and insurance pricing to real-time recommendation engines and trading signals. The range of problems, constraints, and failure modes I have encountered has taught me things outside of what textbook or research papers highlight.

That is what this blog is about. Not theory in isolation, but the hard-won lessons from applying machine learning where the stakes are real: where a model's output drives business decisions, where business managers need transparency on a model's behavior, and where failure has tangible consequences. The gap between an interesting algorithm and a reliable production system is vast, and it is in that gap that most business value resides.

In future posts, I will write about data riddles, model design, unusual feature engineering, explainability, and the pitfalls I have encountered along the way. Whether you are an executive or manager responsible for the projects that depend on these systems, or a data scientist or machine learning engineer building them, I hope you will find practical, honest insights here from a mathematician who has spent two decades tackling these questions in the trenches.

If any of this resonates or you see things differently, I would enjoy hearing from you.