Snacks Weekly on Data Science cover art

All Episodes

Snacks Weekly on Data Science — 142 episodes

#
Title
1

Forecasting Models for Airport Marketplace Operations [Uber]

2

Accelerating Experimentation Velocity with Interleaving [Expedia]

3

Building Taxonomies with Large Language Models [Microsoft]

4

Fraud Detection with Multi-Agent AI Architecture [Razorpay]

5

Hybrid Search for Improved Content Discovery [OLX]

6

Localization-Led Generative AI Product [Udemy]

7

Ladder of Evidence to Understand Product Effectiveness [Meta]

8

Customized AI System for Subtitle Translation [Vimeo]

9

Scaling Unit Test Coverage with AI Tools [NYTimes]

10

Product classification evolution [Shopify]

11

Building an Ads System from Scratch [Faire]

12

Optimize SQL Stored Procedures with LLM [Agoda]

13

LLM-Empowered Job Search [LinkedIn]

14

Personalized CRM with Bandit algorithm [Uber]

15

Enhanced Evaluation for Analytics AI Agent [Thomson Reuters Labs]

16

Measure Listing Lifetime value [Airbnb]

17

RankNet and LambdaRank for Enhanced Ranking Models [OLX] 

18

Evolving user intent understanding prediction [Udemy]

19

Framework for Navigating Product Strategy as Data Leaders [Meta]

20

Estimating Incremental Lift in Customer Value Using Synthetic Control [PayPal]

21

Predicting User Session Intent with Multi-Task Learning [Netflix]

22

Product Recommendations with LLMs and Word2Vec [CVS Health]

23

Building AI Agents at Airtable [Airtable]

24

Quick Thoughts and Reflections at the End of 2025

25

Real-time Spatial and Temporal Forecasting [Lyft]

26

GenAI Solution for Invoice Document Processing [Uber]

27

Optimize Web Performance [Walmart]

28

Understanding Metric Movement with Root Cause Analysis [Pinterest]

29

Improving Search Ranking for Maps [Airbnb]

30

Out-of-Stock Product Recommendations with Machine Learning [Instacart]

31

Covariate Selection in Causal Inference [Booking.com]

32

Personalizing Marketing with Uplift Modeling [Klaviyo]

33

Quick History and Fun Facts About Halloween: Pumpkins, Candies, and Costumes

34

Feed Ranking: From Batch Inference to Online Inference [Whatnot]

35

Self-serve Experimentation Tool for Marketing [Tripadvisor]

36

Global Feature Importance with Collective Wisdom [Meta]

37

Evaluating Retrieval Capabilities of Language Models [Microsoft]

38

Personalized Recommendation with Foundation Models [Netflix]

39

A/B Testing vs. Multi-Armed Bandits: A Simulated Study [Vanguard]

40

Catalog Attribute Extraction with Multi-Modal LLMs [Instacart]

41

Segmenting Supply with a Data-Driven Methodology [Airbnb]

42

Causal Inference with Bayesian Structural Time Series Model [Walmart]

43

Advancements in Embedding-Based Retrieval [Pinterest]

44

How Data Scientists Lead and Drive Impact [Meta]

45

Building Scalable Risk Management Platform [Revolut]

46

Tackling Interference Bias with Marketplace Marginal Values [Lyft]

47

Causal Inference with Double Machine Learning [Microsoft]

48

Scalable and Blendable Feed Construction [Whatnot]

49

Using Generative and Traditional AI to Enhance Travel Experience [Expedia]

50

Ensuring Data Quality at Petabyte Scale [Glassdoor]

51

Building a Travel Assistant with LLMs [Agoda]

52

Setting Goals at Scale with the Goal Map [Meta]

53

Predicting user actions with transformer-based models [Hike]

54

Quantization Techniques for Language Model [EsperantoTech]

55

Key Ingredients for a Secure Agentic AI Future [Intuit]

56

Lessons and Best Practices in Online Experimentation [Oda]

57

Predict Booking Cancellations with Survival Modeling [Booking.com]

58

Measure the unit cost of GenAI Features [Workday]

59

Adopt recommendation for property search [Expedia]

60

Evaluate LLM-based chatbots performance [Microsoft]

61

Algorithmic Content Recommendation with Editorial Judgment [NYTimes]

62

Enhancing Conversational AI with LLMs [Airbnb]

63

Emerging Economy of Large Language Models (LLMs) [Wix]

64

Global Holdout Groups [Klaviyo]

65

Scaling Code Reviews with LLMs [Faire]

66

Estimating Long-Run Treatment Effects Using Surrogate Indices [Instacart]

67

Enabling ML Productivity and Efficiency at Scale [Meta]

68

Elevating Product Machine Learning Models with LLMs [Coupang]

69

Ranking Lodgings: Machine Learning Behind the Booking Experience [Expedia]

70

Machine Learning Solution to Personalize Recommendations [Thumbtack]

71

Enhancing Machine Learning model quality with model excellence score framework [Uber]

72

Enhance Customer Ticket Categorization with Generative AI [RazorPay]

73

A Brief Overview of Causal Analysis [Microsoft]

74

Develop a chatbot using customized generative AI solution [Noom]

75

Personal Data Classification [Airbnb]

76

Improving Search Engine Marketing Performance: My First Data Science Project

77

Reward engineering for better content recommendation [Netflix]

78

Adaptive Experimentation for Paid Marketing Optimization [Instacart]

79

Product bundle recommendation with Graph Learning and GPT [CVS Health]

80

Augmentation techniques for imbalanced text classification [Walmart]

81

Optimize delivery picking process with mathematical modeling [Instamart]

82

Building Contextualised Moderation Classifier [GovTech Singapore]

83

Promotion aware demand forecasting for groceries [AFresh]

84

Graph technology in fraud detection and prevention [Booking.com]

85

Marketing mix modeling in marketing Measurement [Qonto]

86

Causal machine learning to power data driven decisions [Urban Company]

87

Advanced Product Categorization with Vision Language Models [Faire]

88

Leverage CUPED to reduce experimentation lifecycle [Walmart]

89

Building video classifiers with vision language models and active learning [Netflix]

90

Measuring Marketing Incrementality with Geo Testing [Expedia]

91

Personalized Out-of-App Marketing Strategy [Uber]

92

Predicting Estimated Time of Arrival (ETA) Reliability [Lyft]

93

Moderating Inappropriate Video Content [Yelp]

94

Measuring brand perception with social media data and deep learning [Airbnb]

95

Empower Decision Making with Regression Discontinuity Design [Instacart]

96

Product Recommendation with Deep Learning and Reinforcement Learning [LinkedIn]

97

Measure Semantic Relevance in Search with Large Language Models (LLMs) [Faire]

98

Making Informed Decisions in A/B Tests with Multiple Metrics [Spotify]

99

Improving ETA Predictions with Advanced Deep Learning Architecture [DoorDash]

100

Forecasting with the balance of art and science [Meta]

101

Optimize Feature Selection with Generic Algorithm [JustEatTakeaway.com/Grubhub]

102

Monitoring Mechanisms for Recommendation Systems [Tubi TV]

103

Determine Causal Effects through Adoptor Analysis [Walmart]

104

Measure Web Performance with Composite Metric [Indeed]

105

Developing Text-to-SQL Feature with Large Language Models (LLMs) [Pinterest]

106

A/B Testing with Cluster Experimentation Under Strong Network Effects [Meta]

107

Measuring Marketing Effectiveness with Geo-experimentation [Grammarly]

108

Monte Carlo Simulatoin for Sampled Success Metrics [Shopify]

109

Building Generative AI Product for Customer Segmentation [Klaviyo]

110

Machine Learning Solution for Failed Job Auto Remediation [Netflix]

111

Measure Technical Debt in Software Engineering [Booking.com]

112

Improving Price Experimentation at Amazon [Amazon]

113

Tackle Position Bias in Uber Eats Feed Recommendation [Uber]

114

Decision Making with Analytical Hierarchy Processing [New York Times]

115

Leveraging Generative AI to Boost Data Analyst Productivity [Intuit]

116

Perturbation analysis of Large Language Models (LLM) [Microsoft]

117

Monte Carlo Simulation to Predict Tennis Game Outcomes [DraftKings]

118

Two-Tower Neural Network Architecture for Candidate Generation in Recommendation System [Expedia]

119

Large Language Model (LLM) with Retrieval Augmented Generation (RAG) Technology for Efficient Agile Planning [Walmart]

120

Automated Sanity Checks to Streamline Machine Learning Deployment [Intuit]

121

Demand Forecasting with Machine Learning Models [Picnic]

122

Handling Online-Offline Discrepancy in Ads Ranking System [Pinterest]

123

Consolidate multiple machine learning models for a better performance [Instacart]

124

Building Recommendation System with Encoder Architecture [ZipRecruiter]

125

Leverage ChatGPT to build claim assistant functionality [Oscar Health]

126

Ads Simulation to Accelerate Advertising Optimization [UberEats]

127

Leveraging Generative AI for Food Recipe Creation [HelloFresh]

128

2024-01-01 How I achieved my 2013 new year resolution through an effective and unconventional learning approach

129

[Special episode] Different types of Data Science work and why I enjoy being a Data Scientist

130

2023-12-18 Product Personalization with Learning to Rank [CARS24]

131

2023-12-11 Optimising Marketing Allocation with Marketing Mix Models [Haleon]

132

2023-12-04 Generative AI solution to create engaging email subject lines [Nextdoor]

133

2023-11-27 Clustering-based customer segmentation [Microsoft]

134

2023-11-20 In-video search [Netflix]

135

2023-11-13 Geo Experimentation [Mercado Libre]

136

2023-11-06 CUPED explained [Statsig]

137

2023-10-30 geospatial search made easy [Walmart]

138

2023-10-23 personalized recipe recommendations [The New York Times]

139

2023-10-16 synthetic search data [Expedia]

140

2023-10-09 label noise problems and solutions [Walmart]

141

2023-10-02-instacart-ads-incrementality

142

Introducing Snacks Weekly on Data Science