Snacks Weekly on Data Science
BookmarkPan Wu
Snacks Weekly on Data Science is a education podcast hosted by Pan Wu. It has 133 episodes, with the latest published April 2026.
This podcast is about making data science and machine learning knowledge accessible and less intimidating. Every week, I will handpick one selected industrial tech blog to break it down. We will discuss some key data science concepts and machine learning algorithms, and how they are applied in those real-world applications.Subscribe to the channel and enjoy Snacks Weekly on Data Science!
education ·en ·133 episodes
Product classification evolution [Shopify]
Building an Ads System from Scratch [Faire]
Optimize SQL Stored Procedures with LLM [Agoda]
LLM-Empowered Job Search [LinkedIn]
Personalized CRM with Bandit algorithm [Uber]
Enhanced Evaluation for Analytics AI Agent [Thomson Reuters Labs]
Measure Listing Lifetime value [Airbnb]
RankNet and LambdaRank for Enhanced Ranking Models [OLX]
Evolving user intent understanding prediction [Udemy]
Framework for Navigating Product Strategy as Data Leaders [Meta]
Estimating Incremental Lift in Customer Value Using Synthetic Control [PayPal]
Predicting User Session Intent with Multi-Task Learning [Netflix]
Product Recommendations with LLMs and Word2Vec [CVS Health]
Building AI Agents at Airtable [Airtable]
Quick Thoughts and Reflections at the End of 2025
Real-time Spatial and Temporal Forecasting [Lyft]
GenAI Solution for Invoice Document Processing [Uber]
Optimize Web Performance [Walmart]
Understanding Metric Movement with Root Cause Analysis [Pinterest]
Improving Search Ranking for Maps [Airbnb]
Out-of-Stock Product Recommendations with Machine Learning [Instacart]
Covariate Selection in Causal Inference [Booking.com]
Personalizing Marketing with Uplift Modeling [Klaviyo]
Quick History and Fun Facts About Halloween: Pumpkins, Candies, and Costumes
Feed Ranking: From Batch Inference to Online Inference [Whatnot]
Self-serve Experimentation Tool for Marketing [Tripadvisor]
Global Feature Importance with Collective Wisdom [Meta]
Evaluating Retrieval Capabilities of Language Models [Microsoft]
Personalized Recommendation with Foundation Models [Netflix]
A/B Testing vs. Multi-Armed Bandits: A Simulated Study [Vanguard]
Catalog Attribute Extraction with Multi-Modal LLMs [Instacart]
Segmenting Supply with a Data-Driven Methodology [Airbnb]
Causal Inference with Bayesian Structural Time Series Model [Walmart]
Advancements in Embedding-Based Retrieval [Pinterest]
How Data Scientists Lead and Drive Impact [Meta]
Building Scalable Risk Management Platform [Revolut]
Tackling Interference Bias with Marketplace Marginal Values [Lyft]
Causal Inference with Double Machine Learning [Microsoft]
Scalable and Blendable Feed Construction [Whatnot]
Using Generative and Traditional AI to Enhance Travel Experience [Expedia]
Ensuring Data Quality at Petabyte Scale [Glassdoor]
Building a Travel Assistant with LLMs [Agoda]
Setting Goals at Scale with the Goal Map [Meta]
Predicting user actions with transformer-based models [Hike]
Quantization Techniques for Language Model [EsperantoTech]
Key Ingredients for a Secure Agentic AI Future [Intuit]
Lessons and Best Practices in Online Experimentation [Oda]
Predict Booking Cancellations with Survival Modeling [Booking.com]
Measure the unit cost of GenAI Features [Workday]
Adopt recommendation for property search [Expedia]
Loading reviews...
Loading similar podcasts...