Skip to main content
Klaviyo Data Science Podcast

Klaviyo Data Science Podcast

By Michael Lawson
This podcast is intended for all audiences who love data science--veterans and newcomers alike, from any field, we’re all here to learn and grow our data science skills. New episodes monthly. Learn more about Klaviyo at www.klaviyo.com!
Listen on
Where to listen
Breaker Logo

Breaker

Google Podcasts Logo

Google Podcasts

Overcast Logo

Overcast

Pocket Casts Logo

Pocket Casts

RadioPublic Logo

RadioPublic

Spotify Logo

Spotify

Klaviyo Data Science Podcast EP 18 | Sparking User Creativity with Showcase
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Fuel for the Creative Fire It’s no secret: being creative is hard. Creativity requires time and energy, at the bare minimum, and lacking creativity can spiral into writer’s block and other such conditions. That may be okay if you’re just sending out a tweet here or there — but what if your core user base consists of people who need to be creative, day in and day out? The Creative team at Klaviyo recently tackled the problem of helping users get inspired to create content, and I sat down to discuss the thinking that went into the resulting feature, Showcase. You’ll hear about the development process for Showcase, but also about the underlying problems that Showcase is trying to solve and the process of coming up with a solution like Showcase. Specific topics include: Using data science to answer questions that seem simple… even when they aren’t Ensuring data privacy in solutions that have to scale Controversial sandwiches, and why they make great marketing tools “There are actually a lot of sites where you can subscribe to literally every single email that a company sends out… but you have no sense of: did these emails do well? What about them was good? Is this something I should copy? It’s just throwing out a bunch of data with no context or insight whatsoever.”  — Charlie Natoli, Senior Data Scientist See the full episode writeup, including links and who's who, on Medium.
41:08
November 29, 2021
Klaviyo Data Science Podcast EP 17 | The Power of Back-of-the-Envelope Math
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Slow Problems, Quick Solutions We’ve devoted quite a bit of time on this podcast to robust, carefully tuned, and vetted-in-a-thousand-ways solutions. This episode, we venture beyond the land of neatly trimmed hedges and into the unknown, where scrappy solutions may be the only ones that are feasible — or even possible. And we’ll hear about settings where a quick calculation on a napkin can be the difference between success and failure — including the biggest weekend of the ecommerce year. You’ll hear about all that and more, including: How to solve Fermi problems (and possibly get put on a watch list) When quick calculations can save hours of painstaking work How even the simplest math can help you prepare for the most complex engineering challenges of the year “We really are talking huge surges here… The systems you really want to watch out for, between the hours of 9 to 11 a.m. on Black Friday, move as much data as they had to move in the month of June.”  — Zac Bentley, Lead Site Reliability Engineer See the full show notes, including the statistical explanations of the paradoxes we discuss, on Medium.
45:08
November 3, 2021
Klaviyo Data Science Podcast EP 16 | Using Data Science to Answer Tough Questions (feat. Plytrix)
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Solving difficult problems with data science This month, we talk with Shane Suazo, the founder of Plytrix Analytics, about using data science to drive efficient business growth. Shane and Plytrix work with Vital Proteins, and we dive deep into their story and highlight the places where using specific — and powerful — data science techniques helped accelerate a growth opportunity into a growth story. You’ll hear about all that and more, including: Establishing a single source of truth as a foundation for advanced analyses Preventing churn with minimal cost The most important advice for translating general data science techniques to the reality of a specific business “It’s enabled Vital Proteins to send more timely messages with more relevant offers — offers that are better-tailored to our high-value customers specifically.”  — Shane Suazo, Plytrix Links Learn more about Plytrix Analytics (Medium, LinkedIn, Twitter, Facebook) Full show notes on Medium About Klaviyo Klaviyo empowers creators to own their own destiny and helps growth-focused ecommerce brands drive more sales with super-targeted, highly relevant email, SMS, Facebook, and Instagram marketing. Interested? We’re always looking for great people to join our team. Who’s who Michael Lawson, Senior Data Scientist Shane Suazo, Founder, Plytrix Edited by: Michael Lawson Logo by: Griffin Drigotas, Ally Hangartner from Klaviyo Design
34:27
October 5, 2021
Klaviyo Data Science Podcast EP 15 | Books every data scientist should read (vol. 2)
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… (More) required reading for data science A question we frequently get asked is: what books should I read to be a better data scientist/machine learning engineer? This may not surprise you, but there isn’t just one answer — in fact, we spent an entire episode talking about three ways to level up your data science knowledge and skills. This month, we’re back with three more: One of the foremost foundational texts for understanding machine learning models in a statistical way A survey course for a broad variety of machine learning models, with the opportunity to go in depth on topics like deep learning A foundational text in designing and analyzing experiments — both in ideal scenarios and in cases where the standard assumptions aren’t met Mentioned this episode We discuss the following books and courses in this episode: The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome Friedman: https://web.stanford.edu/~hastie/ElemStatLearn/ Kirill Eremenko’s A-Z courses on data science, machine learning, artificial intelligence, and deep learning Field Experiments: Design, Analysis, and Interpretation by Alan Gerber and Donald Green: https://wwnorton.com/books/9780393979954 About Klaviyo Klaviyo helps growth-focused ecommerce brands drive more sales with super-targeted, highly relevant email, Facebook, and Instagram marketing. Interested? We’re always looking for great people to join our team. Who’s who Michael Lawson, Senior Data Scientist Nuvan Rathnayaka, Statistician at NoviSci Chad Furman, Senior Software Engineer David Lustig, Data Scientist Edited by: Michael Lawson Logo by: Griffin Drigotas, Ally Hangartner from Klaviyo Design
37:32
September 8, 2021
Klaviyo Data Science Podcast EP 14 | Data Science in the Wild (feat. Super Coffee and Lunar Solar Group)
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Getting real value from data science This week, we talk with Ben Knox from Super Coffee and Gina Perrelli from Lunar Solar Group about using data science to motivate the growth of a business. No hypothetical business cases this week — Super Coffee is a real business with a real growth story, and we’re here to showcase the ways that they have partnered with Lunar Solar Group and used inquisitive problem-solving methods to answer questions core to Super Coffee’s business needs. You’ll hear about all that and more, including: How expert insight translates into valuable questions Dealing with findings that stumped even the experts The data science feature that has helped Super Coffee the most Links Learn more about Super Coffee Learn more about Lunar Solar Group Who’s who Michael Lawson, Senior Data Scientist Ben Knox, SVP Digital, Super Coffee Gina Perrelli (LinkedIn, Website), Co-Founder, Lunar Solar Group Edited by: Michael Lawson Logo by: Griffin Drigotas, Ally Hangartner from Klaviyo Design
26:08
August 3, 2021
Klaviyo Data Science Podcast Ep 13 | How to run a product experiment
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Making your product experiments count We’ve talked about quite a few aspects of data science on this podcast, but one that’s perhaps conspicuously absent so far is running experiments on your product. It’s no secret that experiments provide extraordinarily high-quality data to help you make decisions, but it’s also no secret that you only get good experimental results if you run good experiments. You’ll hear about running a good experiment and more, including: How experimentation fits into the design cycle What sorts of changes can drive unexpectedly large growth How to understand and adapt to counterintuitive results Resources Evan Miller’s A/B testing guide: https://www.evanmiller.org/ab-testing/ Who’s who Michael Lawson, Senior Data Scientist Eric Gravlin, Lead Product Designer Hannah McGrath, Product Analyst II Edited by: Michael Lawson, Aaron Goeglein Logo by: Griffin Drigotas, Ally Hangartner from Klaviyo Design
34:09
July 19, 2021
Klaviyo Data Science Podcast Ep 12 | How data science teams (should) grow
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Recruiting for a data science team Most of us reading this writeup have probably had at least one interaction with a recruiter. Most of us reading this writeup probably don’t have a deep knowledge of recruiting — what recruiters do, how they help teams scale, and what the other 90% of the iceberg you don’t see as a candidate consists of. Recruiters are on the front lines of attracting talent and making sure that a team grows the right way, and this episode we talk about how to make sure that happens. You’ll hear about all that and more, including: Common misconceptions about recruiting The most difficult aspects of scaling a team Why some recruiters hate the one-page résumé Full show notes: https://medium.com/klaviyo-data-science/klaviyo-data-science-podcast-ep-12-how-data-science-teams-should-grow-d1c7005b1dc8
41:46
June 8, 2021
Klaviyo Data Science Podcast Ep 11 | Books every data scientist should read (vol. 1)
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Required reading for data science A question we frequently get asked is: what books should I read to be a better data scientist/machine learning engineer? This may not surprise you, but there isn’t just one answer — depending on the skills you have, your knowledge base, the point of your career that you’re in, and many other factors, there are many books you could read that will help you learn more. This month, we cover several ways to improve the skills you need to contribute to a data science team. You’ll hear about all that and more, including: Object-oriented programming, how to think about it practically, and how it can help anyone on a data science team The ethics of machine learning and AI, and why understanding AI ethics is one of your most powerful tools How Pac-Man delivers some of the most powerful data science insights of our time Mentioned this episode Some more reading or viewing that we mention in this episode: Practical Object-Oriented Design in Ruby by Sandi Metz: https://www.poodr.com/ Sandi Metz’s keynote: https://www.youtube.com/watch?v=8bZh5LMaSmE Weapons of Math Destruction by Cathy O’Neil: https://weaponsofmathdestructionbook.com/ Northeastern CS 4100: https://www.ccs.neu.edu/home/jwvdm/teaching/cs4100/fall2019/ UC Berkeley CS 188: https://inst.eecs.berkeley.edu/~cs188/pacman/home.html Contact us The best place to reach the podcast is by messaging me on Twitter: https://twitter.com/lawson_m_t.
43:27
April 8, 2021
Klaviyo Data Science Podcast EP 10 | Once in a (customer) lifetime
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Understanding your Customer Lifetime Value This is a math-heavier episode than usual — we’re going to dive into probabilistic distributions and talk about systems of estimators. Even if that’s not your background, though, you should still find this episode useful. That discussion is all based in something crucial to real-life businesses around the world: customer lifetime value, or CLV. What exactly does CLV tell you, how exactly is it calculated and predicted, and why exactly does it matter to your business? You’ll hear about all that and more, including: Statistical approaches to modeling customer behavior Difficulties that arise when customers don’t act exactly like they’re modeled How the humble Tungsten cube can teach us about the entire customer journey Contact me The best place to reach the podcast is by messaging me on Twitter: https://twitter.com/lawson_m_t.
31:49
March 23, 2021
Klaviyo Data Science Podcast EP 9 | Measuring up with benchmarks
Benchmarks: what are they and why? You’ve probably heard of benchmarks. You’ve probably even used them. But what exactly are benchmarks, how are they useful, and how can you go about building a system to make benchmarks in your own industry? You’ll hear about all that and more, including: How to use benchmarks to make informed decisions about improving your business Why the humble stoplight served as a key insight for making complex math understandable How to assess your personal levels of spice intake Mentioned this episode Some more reading or viewing that we mention in this episode: 2020 in review using benchmarks: https://www.klaviyo.com/blog/ecommerce-benchmarks-2020-email-marketing The benchmarks feature announcement video, featuring the one and only Data Science Santa: https://youtu.be/Ge5zvOQVLDc?t=298 The Klaviyo benchmarks feature page: https://www.klaviyo.com/features/benchmarks The Klaviyo benchmarks announcement post: https://www.klaviyo.com/blog/benchmarks-ecommerce-performance About Klaviyo Klaviyo helps growth-focused ecommerce brands drive more sales with super-targeted, highly relevant email, Facebook, and Instagram marketing. Interested? We’re always looking for great people to join our team. Contact me The best place to reach the podcast is by messaging me on Twitter: https://twitter.com/lawson_m_t.
33:40
February 17, 2021
Klaviyo Data Science Podcast EP 8 | 2020: a data science year in review
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… 2020 Year in Review We have a bit of a different episode this month. Instead of diving deep into a specific topic, I asked 14 members of the Klaviyo data science team to give their personal highlight for 2020 as a year in data science. You’ll hear about a bunch of fascinating data science topics, including: Using machine learning to take a quantum leap in drug discovery Discovering methods from much older years that are still relevant for the problems of today How 2020 provided some new opportunities — and some sobering real-world stress tests — for data science Full Episode Notes See https://medium.com/klaviyo-data-science/klaviyo-data-science-podcast-ep-8-2020-a-data-science-year-in-review-88be9b534183. Contact Me Contact me on twitter: @lawson_m_t Corrections This podcast was recorded in January 2021, before Abigail Thorn publicly came out as transgender. It currently refers to her by her former name, but will soon be edited. Congrats to Abigail!
46:58
January 19, 2021
Klaviyo Data Science Podcast EP 7 | Laying a Stable Engineering Foundation
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Engineering Challenges in Data Science All data science work at scale rests on a solid foundation of engineering. We discuss how to establish that foundation — from what goes into software engineering to begin with to the specifics of how to prepare for big seasonal events like Black Friday and Cyber Monday. You’ll hear from software engineers on the team about: Why building software is a lot like running a bar How to make things be — or at least seem — real-time How a tiny leak can crash a whole system Full show notes available at https://medium.com/@michael-lawson-96765/klaviyo-data-science-podcast-ep-7-laying-a-stable-engineering-foundation-ba6462aa0db. Contact us: @lawson_m_t on Twitter.
40:33
December 10, 2020
Klaviyo Data Science Podcast EP 6 | Navigating Seasonality in E-commerce
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Seasonality in e-commerce As the calendar changes, so do the right steps to take for your e-commerce business. We wade into the waters of seasonal changes in behavior, data, and logistics, and we take a deeper look at how to navigate them. You’ll hear from data scientists and product analytics about: The fact that gardening is sometimes more powerful than the biggest holiday of the year Why you should stop worrying and love the error bars How to immortalize yourself as a data science meme Full show notes are available at https://medium.com/@michael-lawson-96765/klaviyo-data-science-podcast-ep-6-navigating-seasonality-in-e-commerce-1bac11b8bf13. Contact us: @lawson_m_t on Twitter.
45:06
November 6, 2020
Klaviyo Data Science Podcast EP 5 | How to recommend products and influence people
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… Recommender systems: how do they work? We get recommendations for all sorts of things today: routes to take when we drive, places to eat, books to read, petitions to sign, and of course, things to buy. We take a deeper look at the task of making the data science and software systems that dispense useful recommendations at scale, with a special focus on recommending ecommerce products. You’ll hear from data scientists and engineers about: The best (and worst) recommendations we’ve ever gotten How the recommendation systems you take for granted actually work under the hood Why dining room tables are basically the same thing as people’s favorite colors
46:50
October 5, 2020
Klaviyo Data Science Podcast EP 4 | What Makes Reporting Good?
Welcome back to the Klaviyo Data Science podcast! This episode, we dive into… What makes a report good? Data-centric teams likely take it as a given that good reporting is a key to living a happy life, but what exactly makes a report good? We dive into the topic of reporting and discuss ways to make a report exceed expectations. You’ll hear from data scientists and product designers about: Why bad reports may be worse than no reports Why good reports may be more like the movie Inception than you think How to design reports with your target audience in mind
41:10
September 3, 2020
Klaviyo Data Science Podcast EP 3 | Behind the curtain with form A/B testing
In this episode, we take a deep dive into a recent feature the team built, signup form A/B testing, to give you a taste of what it’s like to build software for data science. You’ll hear from data scientists, product designers, and software engineers. We discuss: The reason multi-arm bandits are called multi-arm bandits How to distill a two-minute explanation into a single word The way people think about randomness, and what that means when you’re designing a feature that involves randomness Questions, comments, clarifications, or concerns? Reach out to Michael Lawson!
36:17
August 6, 2020
Klaviyo Data Science Podcast EP 2 | Starting out in Data Science
In this episode, we discuss how our careers in data science began, lessons we’ve learned along the way, and mistakes we’ve made and learned from. You can expect to hear: When we stopped wanting to be astronauts and started wanting to be data scientists Advice we’d give to anyone just starting in the field Advice we’d give to anyone currently at the helm of a dinosaur-based movie franchise Resources We mention a few books and other resources in the course of this episode. Check them out here: The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome Friedman: https://web.stanford.edu/~hastie/ElemStatLearn/ Statistical Rethinking by Richard McElreath: https://xcelab.net/rm/statistical-rethinking/ Linear algebra: Foundations to Frontiers on edX: https://www.edx.org/course/linear-algebra-foundations-to-frontiers Blog posts: http://www.terran.us/talks/201808_successful_project.pdf, https://www.fast.ai/2018/07/12/auto-ml-1/, https://eng.lyft.com/whats-in-a-name-ce42f419d16c
39:30
July 7, 2020
Episode 1: How to do research (in a pandemic)
We’re excited to unveil the first episode of the Klaviyo Data Science podcast! This podcast is intended for all audiences who love data science--veterans and newcomers alike, from any field, we’re all here to learn and grow our data science skills. We’re jumping right into the action with this episode. This is a deep dive into research in action. We’ll learn about what’s happening in the world of ecommerce in the wake of COVID-19, and more importantly how we figured out what’s happening. We’ll dig into the whole research funnel, from forming a hypothesis, to analyzing and learning, to taking what you’ve learned and iterating again. Also in this episode: Mastering dinner table conversations with friends and family Using automation to win friends and influence marketers How to smell good in quarantine Want to learn more about Klaviyo? Check us out at www.klaviyo.com!
41:13
June 3, 2020