Snacks Weekly on Data Science - Podcasts
Podcast

Snacks Weekly on Data Science

Pan Wu
0 Plays

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!

Latest Episodes

Evaluating ML Approaches for Large-Scale Document Classification [Databricks]

16 Nov 2026
8:38

In this episode, we explore how Databricks compares three approaches to large-scale document classification, with quality, cost, and throughput as production requirements. Vector search offers the lowest cost, adding AI Classify improves accuracy, and direct LLM frontier-model calls face higher costs and context limits. Across the reported benchmarks, retrieving a shortlist before classification delivers the best measured balance of accuracy and cost, while allowing catalog updates without retra…

Compressing LLM Agent context [Shopify]

09 Nov 2026
8:35

In this episode, we discuss how Shopify tackled a recurring cost in its AI agent by compressing detailed system instructions into a smaller learned representation. The approach preserved prediction quality in the team’s evaluations while reducing latency and GPU requirements. As businesses expand their use of LLMs, the cost of processing tokens at scale becomes an increasingly important operational consideration. Approaches like this show how improving serving efficiency can help businesses scal…

Scale Human Labeling with LLMs for Better Search Relevance [Dropbox]

02 Nov 2026
8:23

In this episode, we talk about how Dropbox improved the search ranking performance of one of its key products. The team used a small amount of human judgment to calibrate an LLM, then used the LLM to generate training labels at roughly 100 times the human effort and train a more efficient production ranking model. With this approach, the LLM can scale human judgment, while the human reference set keeps that scaling grounded in correctness. For more details, you can refer to their published tech …

Unifying Ads Engagement Modeling Across Surfaces [Pinterest]

26 Oct 2026
8:58

In this episode, we discuss how Pinterest moved from three independently evolving ads engagement models toward a unified modeling framework. The team started with a simple merged model, then progressively refined it by combining complementary modeling components, adding surface-specific calibration and multi-task learning, preserving surface-specific model exports, and optimizing both model computation and serving infrastructure. The result was a system that could share learning across surfaces …

Predicting Rider Conversion with Sparse Data Using Bayesian Trees [Lyft]

19 Oct 2026
8:01

In this episode, we talk about Lyft’s need to predict whether riders will convert across a wide range of highly specific situations, where the available data becomes increasingly sparse as the situations become more specific. Instead of relying entirely on a global model or trusting noisy local estimates, Lyft built a hierarchical Bayesian framework where specific models can borrow information from broader models. This allows the system to capture local behavior when enough evidence exists while…

Budget Allocation at Scale [Atlassian]

12 Oct 2026
9:15

In this episode, we discuss the budget allocation problem faced by Atlassian when trying to optimize its marketing investment decisions across many channels, products, and geographic markets. The company solved this with a two-stage system: a global payout model that predicts how business outcomes change with spend, followed by a constrained optimizer that finds the best allocation across the entire portfolio. They then added an independent optimizer as a reliability check and connected the syst…

Semantic Search for LinkedIn’s Hiring Assistant [LinkedIn]

05 Oct 2026
8:38

In this episode, we discuss how LinkedIn moves beyond keyword matching to find candidates based on actual qualification fit. The team first created a scalable relevance definition using LLM-based supervision, distilled that knowledge into customized embeddings, and then designed the retrieval, ranking, infrastructure, and evaluation system around that signal. The result was a search system that improved both candidate relevance and recruiter engagement while actually returning fewer candidates. …

Measuring AI Infrastructure Impact with Causal Inference [Meta]

28 Sep 2026
8:50

In this episode, we discuss how Meta measures the business value of shared ML infrastructure when that value appears indirectly through downstream model launches. Instead of relying on adoption, usage, or traditional infrastructure metrics, the team built an observational causal framework around individual model launches. By comparing feasible adopters with comparable non-adopters and controlling for major confounding factors, the team estimated the incremental revenue associated with infrastruc…

Building Taxonomies from Unstructured Text Using LLMs [Microsoft]

21 Sep 2026
9:05

In this episode, we discuss two LLM-assisted pipelines for turning unstructured text into a structured taxonomy with minimal manual annotation. The bottom-up approach lets semantic representations and clustering discover categories from the data, making it useful for open-ended exploration and relatively efficient at scale. The top-down approach starts with LLM-generated categories and recursively classifies and subdivides the corpus, making it more controllable and easier to align with business…

Building Semantic IDs for Product Understanding at Scale [Instacart]

14 Sep 2026
9:17

In this episode, we talk about how Instacart identified a limitation of a standard taxonomy: it could classify products, but it couldn't connect them the way real shoppers do. The team developed a solution around Semantic IDs, which compress product embeddings into hierarchical discrete codes, while contrastive learning and taxonomy-based supervision make those codes more semantically meaningful. The result is a representation that can support better product understanding, catalog quality, and r…

Agent-driven ML Exploration [Faire]

07 Sep 2026
10:58

In this episode, we discuss how Faire addresses a fundamental bottleneck in machine learning development: there are more potential experiments than human scientists can realistically run. They developed Autoscience, giving an AI agent a structured environment where it can plan, execute, evaluate, remember, and continuously refine experiments. What makes the approach effective is not the agent alone, but the combination of a reliable experimentation harness, integration with the existing ML stack…

Building food metadata with LLM juries [DoorDash]

31 Aug 2026
9:32

In this episode, we discuss how DoorDash built a reliable metadata generation platform that could operate across millions of constantly changing menu items. The solution combined multimodal generation, automated evaluation through LLM juries, optimization loops for improving model behavior, and distributed infrastructure for cost-efficient scaling. By transforming unstructured menu information into precise, structured attributes, DoorDash unlocked many new product capabilities that ultimately he…

Scaling subscriptions with causal machine learning [NYTimes]

24 Aug 2026
10:33

In this episode, we explore how The New York Times built a real-time decision system that estimates the causal impact of different paywall actions, optimizes those decisions based on business objectives, and continuously measures performance using long-term business outcomes. The result is a more flexible and personalized subscription experience that balances immediate conversions with long-term growth. For more details, you can refer to their published tech blog, linked here for your reference:…

Recommending Travel Destinations [Airbnb]

17 Aug 2026
10:00

In this episode, we explore how Airbnb built a destination recommendation model to predict the places users are most likely to travel to next. The model predicts travel intent using sequences of user actions, carefully designed training examples for both active and dormant users, and multi-task learning to capture geographic relationships. Together, these design choices led to more relevant recommendations and measurable improvements across multiple recommendation products. For more details, you…

Building AI Second Brain for Knowledge Workers [Meta]

10 Aug 2026
9:54

In this episode, we discuss how Meta built an AI system with persistent memory, structured organization, secure access to enterprise tools, and reusable workflows. The result was an AI assistant that could participate in ongoing work rather than isolated chat sessions. By carefully organizing knowledge and retrieving only the context relevant to the current task, the system enabled the assistant to deliver more relevant answers and ultimately helped employees work more productively. For more det…

Scaling Experimentation Quality [Booking.com]

03 Aug 2026
10:00

In this episode, we explore how Booking.com scaled experimentation quality across the organization. Instead of relying on strict enforcement, the team chose to optimize for flexibility while building the supporting processes to foster a strong experimentation culture, defining a clear framework for measuring experimentation quality, and integrating those practices directly into the experimentation platform so that good behavior became the default. The combination of improved tooling and sustaine…

Evaluating Show Synopses with LLM-as-a-Judge [Netflix]

27 Jul 2026
12:03

In this episode, we discuss how Netflix built an LLM-based evaluation framework for creative writing quality without losing the nuance that makes expert review valuable. They achieved this by creating a golden dataset calibrated by expert writers, splitting evaluation into specialized judges for each quality criterion, and applying targeted techniques—tiered reasoning, consensus sampling, and multi-agent verification—tailored to the unique needs of each criterion. For more details, you can refer…

Improved Candidate Generation with a Two-Tower Model [Glassdoor]

20 Jul 2026
10:21

In this episode, we explore how Glassdoor customized the Two-Tower model for its specific production environment. The gap between generic semantic embeddings and behavior-driven embeddings proved significant, and closing it required thoughtful decisions regarding training data, negative sampling, and auxiliary learning signals. For more details, you can refer to their published tech blog, linked here for your reference: https://medium.com/glassdoor-engineering/improving-embedding-based-candidate…

Measuring Rider Experience Impact with Causal Inference [Lyft]

13 Jul 2026
10:34

In this episode, we talk about why Lyft needed to understand which rider experiences drive long-term retention. We discuss how raw observational data can produce misleading conclusions because of confounders such as geography, and how Lyft's Rider Experience Score addresses this challenge using Augmented Inverse Propensity Weighting. This doubly robust causal inference method adjusts for those confounders and produces experiment-quality estimates without running an experiment. For more details, …

Unified Ranking for Ads and Organic Recommendations [Flipkart]

06 Jul 2026
8:47

In this episode, we explore how Flipkart rethought ranking in its "Similar Products" widget. Instead of relying on fixed ad slots, the team built a unified ranking system that enables sponsored and organic products to compete on the same playing field. By combining a unified ranking model with a score normalization layer, the system ranks content based on contextual merit rather than predefined positions. The result: higher organic orders, increased ad revenue, and a better overall marketplace e…

Podcasts

Comments & Reviews0