Podcast
From Theme Parks to Tesla: Building Data Products Through Applied ML and Full-Stack Engineering
Open original DataTalks.Club episode
From Theme Parks to Tesla: Building Data Products Through Applied ML and Full-Stack Engineering
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
Episode Overview
How can theme parks use data to cut wait times and guide visitors in real time? In this episode, Abouzar Abbaspour — an EngD-trained machine learning and data engineer whose career spans telecom, e-commerce (bol.com), theme parks (Efteling) and automotive (Tesla) — walks through building systems that optimize visitor flow using crowd modeling, queue prediction and real-time recommendations.
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Podcast Introduction & Event Info
- 1:17 - Early Career: Software Engineering to Data Science
- 2:06 - Academic Path: Professional Doctorate & TU Berlin
- 4:48 - Research Partnerships: Industry Projects and Applied Research
- 6:17 - Efteling Insights: Theme Park Tech and Experience Design
- 7:36 - Crowd Modeling: Queue Prediction and Ride Capacity
- 12:59 - Visitor Routing: Next-Best-Action Recommendation System
- 14:50 - App Adoption & Incentives for Data Collection
- 16:40 - Behavioral Route Modeling & Probabilistic Recommendations
- 18:29 - E-commerce Recs: Bol.com Favorite-Brand Carousel
- 24:03 - Recommendation Validation: Employee Swiping Experiment & A/B Testing
- 26:01 - Real-time Processing: Streaming for Live Experiments
- 31:19 - Measurement & Rollout: Engagement Metrics and Accuracy Results
- 33:21 - Role at Tesla: Data Engineering vs. ML Engineering Responsibilities
- 34:21 - Full-Stack Data Work: Building Apps, Instrumentation, and Deployment
- 41:43 - LLMs & AI-Assisted Development: Productivity Gains and Risks
- 46:06 - On-Prem Inference Hardware: Raspberry Pi, Jetson Orin, Mac Mini
- 49:53 - Models & Platforms: LLaMA, Code Models, and Replicate
- 54:03 - Interview Preparation: Tesla Data Engineering Expectations (Architecture,
- 57:43 - Career Strategy: Prioritization, Learning Opportunities, Underpromise & Overdeliver
- 1:00:10 - Episode Closing & Key Takeaways