9 Interview questions on K Means clustering | Data Science Interview Questions and answers

[@RohitKumar-su8pk]

helpful sir

[@UnfoldDataScience]

Thanks Rohit.

[@swethanandyala]

i completed watching all ur question bank videos...amazing work...thank u so much

[@UnfoldDataScience]

Thanks Swetha for your kind words. It means a lot.

[@anu.s3283]

Thanks much Aman..This series is so useful..Exactly what we get in interviews..I was asked about categorical data in kmeans....but i didnt expect then

[@UnfoldDataScience]

Thanks for watching.

[@roopagowda9271]

Very helpful...

[@kaanonderofficial]

That was a great video Aman. We are waiting more videos .. :)

[@yaarana514]

Thank-you so much i downloaded all videos on clustering .sir also make a video on factor analysis and between difference

[@vaibhav1468]

It's really very helpful series. Sir, please continue this series. The placement season would start from 25 July. Please complete the playlists before 20 July.

[@UnfoldDataScience]

Will put together as much as I can.

[@vaibhav1468]

@@UnfoldDataScience thanks sir.

[@ashishsarathe8248]

It would really helpful Aman keep updating us 👍

[@UnfoldDataScience]

I will try my best

[@svk1869]

Please make video on KNN algorithm interview questions also

[@murapakaganesh1108]

Please do the video on kmeans ++ clustering it is a humble request sir

[@arvindadari3390]

Working on Categorical data is a tricky part but still there are approaches to calculate distance for categorical data by creating Distance Term Matrix and then Using Jaccard distance or simple matching distance methods to find out the distances for categorical data

[@UnfoldDataScience]

Ye Arvind, however of you have like more than 80% data as categories, why to process this approach just ro run k means. I m happy to be challenged.

[@ShivamT13]

Sir I have watched a mock interview where you have asked what is "k" stands for, and why only "k" not l,m,n etc. Could you please answer. 🙏🏻

[@sarans3185]

If over lapping occurs inbetween data than how to cluster it sir can explain in a different vedio

[@UnfoldDataScience]

Ok