Principal Component Analysis (PCA) in Machine Learning: Easy Explanation for Data Science Interviews

Questions about Principal Component Analysis commonly appear in data science interviews. In this video, I’ll explain what principal component analysis is, how it works, the problems you would use PCA for, and the pros and cons associated with PCA.
🟢Get all my free data science interview resources
www.emmading.com/resources
🟡 Product Case Interview Cheatsheet www.emmading.com/product-case...
🟠 Statistics Interview Cheatsheet www.emmading.com/statistics-i...
🟣 Behavioral Interview Cheatsheet www.emmading.com/behavioral-i...
🔵 Data Science Resume Checklist www.emmading.com/data-science...
✅ We work with Experienced Data Scientists to help them land their next dream jobs. Apply now: www.emmading.com/coaching
// Comment
Got any questions? Something to add?
Write a comment below to chat.
// Let's connect on LinkedIn:
/ emmading001
====================
Contents of this video:
====================
00:00 Introduction
00:35 What is PCA?
05:25 Steps in PCA
09:30 Pros and Cons

[@mohsinakbar3357]

Hello Emma, thank you for these interview videos, simple, clear and precise and to the point. Appreciate the work you're doing, keep it up!

[@AllieZhao]

Wonderful videos! Two points to be added: PCA can be very helpful when used in exploratory data analysis and sometimes the principle components from PCA is good way to interpret because they are kind of group the initial features into meaningful components.

[@nickytan3460]

Waiting for you to release digital handbook for this, definitely going to support it😍

[@100IQu]

Thank you for the video. There is one confusing part. You say principal component 1 is in the direction that captures maximum variance. Principal component 2 is in the direction that captures 2nd highest variance. If you tilt the PC1 just a little, it will be the component that captures second highest variance right?
I understand that you mean that PC2 captures the highest variance that remains after removing variance PC1 has captured.
Or you could say that PC2 is the one that captures second highest variance and is also orthogonal or perpendicular to PC1.
I hope you continue to make videos like these that explain data science concepts well even though they get fewer views than your other types of videos. Hopefully, one day, if one has to become a good data scientist, all one has to do is watch your videos at least for ideas that aren't usually explained clearly like Gradient Boosting in decision trees etc.

[@newbie8051]

Was revising my DL course-notes and was confused abt PCA, went through your explanation twice and voila...
After that, to check if I understood this correctly, I even taught this topic to my roommates too !! Thanks a ton !

[@emma_ding]

Thank you for your comment! I'm so glad you found my video helpful enough to even teach your roommates. 😊 That's such a wonderful way to solidify your own learning, too! 😉

[@user-vq6bw2je7r]

Great tutorial! Thanks for sharing this valuable content.

[@chandansagar212]

Thank you !!

[@romangirin772]

Cool video! Thank you!!! About limitations of PCA I would add that it's just linear transformation of features' space. Often this is not enough, so MDS and, of course, tSNE methods are used

[@gobo187]

Can you please also share link to Notion as that can help to read.

[@emma_ding]

Thanks for asking! You can download all the PDFs of my Notion pages at www.emmading.com/get-all-my-free-resources. Enjoy!

[@SonuKumar-gt5xs]

Hi Emma,
these videos are really good.
can you make a video on time series analysis

[@emma_ding]

Thanks for your suggestion! I've added it to my content idea list. ✏️😊

[@emma_ding]

Many of you have asked me to share my presentation notes, and now… I have them for you! Download all the PDFs of my Notion pages at www.emmading.com/get-all-my-free-resources. Enjoy!

[@---zg7ex]

我初中时候班里男同学最喜欢的就是一个叫emma的女同学，成绩超好，长得也美😏