Yelp Data Science Interview

75 million unique visitors visit Yelp monthly.

Vimarsh Karbhari
Acing AI
3 min readFeb 5, 2019

--

Yelp was founded in San Francisco in July 2004 by former PayPal employees Russel Simmons and Jeremy Stoppelman which are part of the Paypal Mafia. Yelp users have contributed over 100 million reviews of almost every type of local business, from restaurants, boutiques and salons to dentists, mechanics, plumbers and more. Yelp is a verb today specially for the kind of data it has and the kind of reviews it provides. Such a high usage site and mobile App generates huge amounts of data which is definitely a treat for a Data Professional.

Interview Process

The first part of the interview consists of a hiring manager interview which is about basic Data Science projects on your resume or background. This is followed by two technical phone screens. One concentrates on a project detail(based on your resume) and maybe python coding questions. The second one is about SQL, product questions, A/B testing questions and python coding questions. The product manager conducts one of these interviews. Onsite interviews are more with the Data team and Data Scientists. It may also have Product Managers on the panel.

Important Reading

Source: MySQLStreamer

Yelp Data Science sits within the Engineering team with close ties to the product team. Data team does drive a lot in the product. Their engineering blog shares their great story in Data Science.

AI/Data Science Related Questions

  • Whats the difference between decision trees and extreme boosted trees mathematically?
  • How to evaluate the features classifying spams and emails.
  • What is the difference between Bayesian vs frequentist statistics?
  • How would you set up A/B tests to improve engagement on Yelp?
  • What features would you use to predict the number of likes on a review?
  • How to swap two elements of a list?
  • List the strings that are anagrams from a set of strings
  • If you had to propose a new Yelp feature, what would it be?
  • What is an n-gram?
  • Determine if a word has a palindrome anagram.

Reflecting on the Questions

Yelp’s business in their data. The data around restaurants, businesses and the reviews is their USP. The data team structure is unique as it sits within the Engineering team which has great infrastructure skills and product team which drives the product roadmap. They use Kafka, Spark, Hadoop and a plethora of other services on AWS. Good learning about their entire stack and great ML skills can surely land you a job at the world’s largest review site.

Subscribe to our Acing AI newsletter, I promise not to spam and its FREE!

Thanks for reading! 😊 If you enjoyed it, test how many times can you hit 👏 in 5 seconds. It’s great cardio for your fingers AND will help other people see the story.

The sole motivation of this blog article is to learn about Yelp and its technologies helping people to get into it. All data is sourced from online public sources. I aim to make this a living document, so any updates and suggested changes can always be included. Please provide relevant feedback.

--

--