The Randstad, Netherlands
Machine Learning leader with 17+ years of experience building and scaling teams, production ML systems, and platforms, spanning both ML science and engineering across global consumer tech and financial services. Currently leading the Traveller Intelligence ML track at Booking.com, managing three ML teams (25+ scientists and engineers) responsible for personalization, ads optimization, and cancellation intelligence systems that directly drive revenue, marketing efficiency, and company-wide experimentation. I operate at the intersection of ML research, engineering, and product — leading the design and delivery of reliable, low-latency ML systems, productionizing applied research on shared platforms, and turning large-scale behavioral data into decisioning capabilities used across the business. I hold a PhD (cum laude) in Econometrics and bring deep expertise in personalization, ranking & recommendations, forecasting, causal modeling, and ML infrastructure. I build high-performing teams, raise technical standards, and deliver ML capabilities that operate reliably at scale.
Lead the Traveller Intelligence ML track, managing three ML teams (25+ scientists and engineers) responsible for large-scale personalization, advertising optimization, and cancellation intelligence systems that directly drive revenue, marketing efficiency, and company-wide experimentation. • Own strategy and execution for user intent modeling, real-time traveler profiling, and predictive decisioning systems used across the traveler journey • Architect and scale low-latency ML systems powering personalization and forecasting for the Connected Trip strategy • Deliver ML-driven intelligence that informs marketing spend allocation, financial planning, discounting, and core experimentation metrics • Partner closely with Central ML and Engineering to leverage and improve shared platforms, tooling, and data infrastructure • Hire, coach, and grow senior ICs and managers while building a high-performing, delivery-focused ML organization
Led the User Intent Modeling team (~10 scientists, engineers, and product) delivering real-time personalization and decisioning systems embedded in Booking’s Customer Data Platform to optimize traveler experience, cross-sell, and advertising outcomes. • Designed and scaled low-latency ML systems for traveler profiling, intent modeling, and journey-level personalization across millions of daily interactions • Established a scalable “model factory” architecture with shared embeddings and sequence-based learning to accelerate experimentation and productionization • Applied modern ML approaches including Transformers, deep neural networks, uplift modeling, and bandits/off-policy learning to model customer intent and causal impact • Operated at global scale on Snowflake/Spark and streaming infrastructure, enabling reliable, high-throughput real-time inference
Built and scaled two ML teams from scratch (~10 scientists and engineers), delivering personalization and recommendation systems across both sides of Booking’s two-sided marketplace (partners and travelers). • Built and productionized ML systems supporting partner lifecycle optimization and traveler personalization throughout the booking journey • Developed recommendation and segmentation models to improve relevance and marketplace matching • Applied techniques including gradient boosting, deep learning, uplift modeling, bandits, and causal inference • Operated at global scale on Hadoop/Spark infrastructure with reliable, low-latency production inference
Deliver professional training programs in applied data science and machine learning for practitioners and technical teams. Teach topics including supervised learning, deep learning, NLP, feature engineering, and production ML using Python and R. Courses accredited by the Netherlands Society for Statistics and Operations Research. Designed and delivered multi-day courses and bespoke programs for experienced analysts, engineers, and PhD researchers.
Member of the Data & Analytics leadership team for Private Banking, leading Data Science and Marketing Automation teams delivering production data and ML products. • Managed cross-functional team of data scientists and analysts building customer journey, prospecting, and trigger-based personalization systems • Consolidated data science and marketing analytics into a single delivery organization to improve execution and impact • Delivered ML-driven decisioning and automation supporting digital engagement and customer experience initiatives
Led one of the bank’s core data science teams delivering production ML solutions across operations and customer journeys, with a focus on NLP and time-series forecasting. • Built and deployed ML systems for email routing, information retrieval, planning, and debt collection, embedded directly into operational workflows • Implemented models on Azure/Databricks and improved the path from prototyping to production • Served on the bank-wide Data Science Review Board, contributing to modeling standards and best practices across teams
Founded a small training initiative delivering applied data science and programming workshops for professionals and early-career practitioners.
Built and productionized machine learning models across retail, commercial, and operations domains, deploying systems on Hadoop/Spark at enterprise scale. • Led the initiative to standardize ML tooling and automate the path from prototyping to production, improving reliability and time-to-deployment across teams • Developed and deployed gradient boosting and deep learning models in production • Active contributor to the internal data science community through mentoring, knowledge sharing, and conference organization