Crack the Data Scientist Case Interview by an Ex-Google Data Scientist

Подписаться 30 тыс.

Просмотров 60 тыс.

50% 1

📈 Got a case interview lined up? Check out: datainterview.com/
====== Details ======
This is a 30-minute guide on how to crack the data scientist case interviews by Dan, a data scientist who previously worked at Google and PayPal. He details a 5-step (clarify, constrain, plan, method and conclude) framework to effectively respond to a case question asked in statistics, ML and product-sense interviews.
In addition, he provides an inside scoop on how interviewers evaluate a candidate's response. Lastly, he covers a preparation strategy for a case interview and walks through an interactive exercise with viewers.
Make sure to subscribe, and hit the 'like' button :)
====== Timestamps ======
0:00 Intro
0:37 Topics Covered
1:08 What Is a Data Science Case Problem?
3:10 Example Problems
4:23 Response Framework
13:36 Evaluation Process
17:45 Preparation Strategy
22:27 Interactive Exercise
====== Connect ======
📗 LinkedIn - / danleedata
📘 Medium - / datainterview

Опубликовано:

30 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 38

@1220MrCool 2 года назад

Honestly all of this prep for a single interview is a full-time job itself.

@DataInterview 2 года назад

I know the pain, been there multiple times. But hopefully it’s well worth it at the end - Dan

@1220MrCool 2 года назад

@@DataInterview I will give this a shot for my own practice and benefit. Thank you kindly!

@1220MrCool 2 года назад

@@DataInterview What is a better way to understand business terminology tied to predictive models for any arbitrary business? I don't have business knowledge to understand the ways to go about these things (lack of business experience while using DS), so how do I learn about them if companies don't release their models?

@cliffrunner Год назад

it is more. a full-time job doesn't need you to do A/B testing, data ETL, model POC, model serving, and product understanding etc. at the same time

@vardhini2240 Год назад

Ngl

@jessyzh917 2 года назад

Very useful content, and you made it so easy to follow and articulate the main points to keep in mind. Thanks so much Dan.

@khizarsultan3316 2 года назад

Thank you Dan for sharing one of the best pieces of content on the Data Scientce Case Interview, Would you please also provide guidance on CV/Resume format for Data Science positions at FAANG. Appreciating in Advance!

@ramnapper2010 Год назад

The youtube algorithms of July 2023 decided I should view your video....what a great video on concepts, insights, and guidance! I'll check out more of your content.

@leelavathigarigipati3887 2 года назад

Very useful content to approach any use cases in data science interviews. Thank you Dan!

@cliffrunner Год назад

I totally agree that the case study is really tricky. Unless you have encounter similar problems before, ti is very difficult to come up with a good approach in a 15 min timeframe. To be honest, in real work, nobody is gonna ask you to present a solution in mins. Any realistic and practical solution requires days, even months of work. That being said, this type of interview is nothing but a 'leetcode' type of test: find some case study questions (especially for the company you are interviewing with), and practice over and over again. It is easier to prepare for big tech where you can find plenty of questions online that smaller companies.

@joseharper3314 5 дней назад

How did I not see this before the last 5 case studies I bombed 😢. Ty!! 😊

@satyam4096 2 года назад

Great way to approach case study questions

@ayushishrivastava9 2 года назад

Golden content!!! Looking forward to more of such videos on approaching/cracking FaANG Data Science case studies problems 😍

@shakkey 4 месяца назад

@Sneha151289 11 месяцев назад

Best content for interview prep!

@artemmoshnin5675 2 года назад

Thanks a lot! It's very useful!

@nikhilshingadiya7798 2 года назад

I want to add in last your case study(driver), sometimes our past data is not enough for churn predication. we needs conduct survey in such way that the we can measure driver actual psychological,physical and financial condition this features(we can use likert scale) will help us to minimise our churn predication.