HomeНаука и техникаRelated VideosMore From: Thales Sehn Körting

How data mining works

866 ratings | 203641 views
In this video we describe data mining, in the context of knowledge discovery in databases. More videos on classification algorithms can be found at https://www.youtube.com/playlist?list=PLXMKI02h3_qjYoX-f8uKrcGqYmaqdAtq5 Please subscribe to my channel, and share this video with your peers!
Html code for embedding videos on your blog
Text Comments (88)
Fred Hm (6 months ago)
This is the BEST explanation i found so far , so thanks a lot!
Thales Sehn Körting (4 months ago)
Thanks a lot. Please like and share the video and subscribe to my channel. Regards
Yan Sant'Anna (12 days ago)
Thanks for explain!
Mr Nobody (28 days ago)
Thank you Dr Körting, very straightforward and useful. I enjoy your videos.
Thales Sehn Körting (27 days ago)
Thanks for your feedback, please like and share the video and subscribe to my channel. Regards
Sadhasivam Raman (1 month ago)
Please give some tips to select the data target
Sadhasivam Raman (1 month ago)
How to select the data target
Thales Sehn Körting (1 month ago)
Thanks for your feedback. Please subscribe to my channel. I would recommend the software WEKA which has the feature selection capacity, several algorithms to select the best attributes among a list of several ones. You can even prepare your data in a CSV file in the format ID, ATTRIBUTE_1, ... ATTRIBUTE_N, CLASS Regards
Marco Serena (4 months ago)
Thanks again and also thanks for your english pronuciation (slow and precise speaking is the best for me due to the fact that english is not my mother tongue)
Thales Sehn Körting (4 months ago)
Many thanks for your feedback. Please like and share the video and subscribe to my channel. Regards
Javier Jugo (5 months ago)
Good but drink a coffee
Thales Sehn Körting (5 months ago)
Thanks, pay me a coffee and subscribe to my channel. Regards
Master Oogway (6 months ago)
Where's the kung fu?
Thales Sehn Körting (4 months ago)
I don’t know. Please subscribe to my channel. Regards
Oscar Monroy (6 months ago)
I am hoping there is more to life than data mining. This truly seems like a horrible existence.
Thales Sehn Körting (6 months ago)
For sure. But in case you still want to study data mining subscribe to my channel. Regards
G Dragon1 (7 months ago)
thank you so much!
Ashhal Syed (7 months ago)
K is silent in Knowledge
Thales Sehn Körting (4 months ago)
Thanks for the correct suggestion. Please liKe (at least here K is not silent) and share the video and subscribe to my channel :) Regards
Juliette Ng (9 months ago)
Thanks for sharing This will help all new intern
Thales Sehn Körting (9 months ago)
thanks for your positive feedback Please like and share the video and subscribe to my channel Regards
Vishnu Nath (11 months ago)
No volume in this video.. can you help !!
Thales Sehn Körting (11 months ago)
Thanks for this feedback. Sorry for this specific problem of the low volume in the video. The solution I gave was to produce subtitles, that helps you to follow the video. I contacted YouTube to substitute the audio, but they do not allow, unfortunately. Please subscribe to my channel. Regards
alimuttaleb alfatlawi (11 months ago)
Thales Sehn Körting tq a lot for explanation but I have some info confused and still not got it yet I need like examples ! How the Data mining work in our life or figures to put some examples names of animles and show us how to work also My warm regards
AskillZ (1 year ago)
It is well explained but super boring. Make it more frenetic pls
AskillZ (1 year ago)
Thales Sehn Körting lol, I will make sure to do that
Thales Sehn Körting (1 year ago)
+AskillZ thanks for your feedback. Want more boring videos? Subscribe to my channel. Regards
Kaz Tee (1 year ago)
Hi how can you decide from dataset that has 1000 rows and 21 columns which to use depending on your research are relevant. How can I reduce the data. What are the effects trying and need to create predictions regression and decision tree can you please help
Joshua Wilson (1 year ago)
great video buddy!
Thales Sehn Körting (1 year ago)
+Joshua Wilson thanks for your feedback Please Like and Share the video and subscribe to my channel Regards
Rajesh Antony (1 year ago)
Really great video explanation of data mining. Simple to understand. Thank you Thales
Thales Sehn Körting (1 year ago)
+Rajesh Antony thanks for the positive feedback. Please like and share the video and subscribe to my channel. Regards
Rahul Raj (1 year ago)
For simple explanation of concept in data mining visit my blog https://dataminingsimpleexplanations.blogspot.in/
GabriellaTM94 (1 year ago)
Great explanation, as usual. Thank you!
Thales Sehn Körting (1 year ago)
+GabriellaTM94 many thanks for your feedback please subscribe to my channel, like and share the video regards
Thiago Villa (1 year ago)
are you Brazilian?
Thales Sehn Körting (1 year ago)
Sim \o/ obrigado por assistir o vídeo, se possível inscreva-se no canal. Abraço
blazortheepic03 (1 year ago)
NICE this REALY helped with my homework. i liked and subscribed
Thales Sehn Körting (1 year ago)
thanks a lot for this feedback, regards
Jessica Rozinha (1 year ago)
Man, i thought my english sucks
Thales Sehn Körting (1 year ago)
Thanks for your feedback. In case you still want to learn Data Mining, mute the video and use the options to display subtitles :) Regards
Alan Zanão (1 year ago)
Great video! Simple and efficient!
Thales Sehn Körting (1 year ago)
Thanks for your feedback Please like/share the video and subscribe! Regards
Nana Boateng (1 year ago)
Very useful video.....thanks a lot
Thales Sehn Körting (1 year ago)
thanks for your feedback please like/share the video and subscribe to my channel regards
vijay (1 year ago)
kojja lanja
Rahul Sharma (1 year ago)
im not from this area but found the tutorial very simple and good , thank you.
Thales Sehn Körting (1 year ago)
thanks for your feedback please like/share the video and subscribe to my channel regards
Zineb EL MOTTAKI (1 year ago)
soooo helpful thanks
Thales Sehn Körting (1 year ago)
thanks for the feedback! Please like/share the video and subscribe. Regards
izzy streaks (1 year ago)
your accent is great bro <3
Gabriel Ventura (1 year ago)
Thales Sehn Körting i think a recognize it, do you speak brazillian portuguese?
Thales Sehn Körting (1 year ago)
thanks for the feedback :) please like/share the video and subscribe to my channel, ok? Regards
Miguel Grandez (1 year ago)
Good video thanks
Thales Sehn Körting (1 year ago)
Hi Miguel, thanks for your feedback Please like/share the video and subscribe. Regards
Steve Walczak (2 years ago)
Thanks Thales for a great video. It was short and to the point. I will be pointing my students here. One question I see that you get over and over again is about the problems of correlated data. Another reason to find uncorrelated data is that many knowledge discovery engines and tools, such as neural networks and almost every statistical package do not work with with highly correlated variables. That is because if you end up using two or more correlated variables in a prediction algorithm, the correlated variables tend to bias the direction of the prediction to be based on what those variables represent. So if you are using five variable, three correlated and two independent, then the three correlated variables own 60% of the influence on the outcome (potentially, assuming the prediction engine starts with balanced effect).
Thales Sehn Körting (2 years ago)
Thanks a lot for your feedback! Please subscribe to my channel and like the video. I agree with you, and hope that many viewers of my video will read your message, because it explains better what I was trying to say in the video, and also in some of my comments. Thanks again, regards
Hannes Fischer (2 years ago)
Thales, ficou show, se tem este material em português? Uma sugestãozinha... na parte de transformação... eu explicaria o que você colocou nos comentários abaixo, pois do jeito que aparece no vídeo não fica claro, o resto está bem claro. Abraços!!
Michelle Inoa (1 year ago)
H cm wn a v de b as.
Thales Sehn Körting (2 years ago)
+Hannes Fischer Eu compartilhei o prezi 'Mineração de dados' com você: https://prezi.com/vjrgzy5qmnvw/
Thales Sehn Körting (2 years ago)
+Hannes Fischer Olá muito obrigado pelo seu comentário Vou tentar inserir a parte de transformação no vídeo. Não se esqueça de se inscrever no meu canal. Um abraço
Nill Bandi (2 years ago)
why is correlated data useless ? why do we have to make it uncorrelated ?
Thales Sehn Körting (2 years ago)
+Nill Bandi thanks for your feedback, please subscriber to my channel and share this video with your peers one thing with highly correlated data (supose 2 vectors) is that "on the limit" we will have two vectors with the same information. and concerning that nowadays we have a lot of information, our algorithms would have to process 2x the same thing (think about 1 billion instances on each vector). regards
Nill Bandi (2 years ago)
+Nill Bandi and thanks for the good video (y)
CrazyFanaticMan (2 years ago)
it seems very common sensical
Thales Sehn Körting (2 years ago)
+CrazyFanaticMan thanks for your feedback, please subscribe to my channel. Indeed it is very common sensical, but someone (please see the references at the end of the video) put of these steps together and decided to call it KDD (most people call Data Mining). Regards
Andran Donan (3 years ago)
Too abstract for me to understand why thats data processed in first place? Is that something useful to bitcoin network or just random data?
Thales Sehn Körting (2 years ago)
thanks for your feedback please like the video and subscribe regards
Cindy Lévano Goldberg (2 years ago)
I agree with you, Thales. Applies to any data in study.
Thales Sehn Körting (3 years ago)
+Andran Donan the proposal to preprocess data is to remove spurious data, fill "gaps" in information, find outliers and etc. This workflow is assumed to work in every type of data. Regards
mixc8 (3 years ago)
Excellent video got me up speed quickly!
Thales Sehn Körting (3 years ago)
+mixc8 thanks for your feedback. Please subscribe to my channel and share this video with your peers
ahmed obeid (3 years ago)
Hi , how can we implement these algorithm that you mentioned in the video to create patterns.
ahmed obeid (3 years ago)
+Thales Sehn Körting Thank you very much.
Thales Sehn Körting (3 years ago)
I suggest to use software weka. regards
Rabiai Tarek (3 years ago)
what a great video !! thank you sir for making this awsome presentation , i became a fan really :)
Thales Sehn Körting (3 years ago)
+Hadil Kaydar Dear friend, thanks for your feedback.Please subscribe to my channel and share this video with your peers. Regards
siva ultimate (3 years ago)
Dear Thales, It was an awesome presentation!! very happy to learn from you now and ever.. Subscribed!
Thales Sehn Körting (3 years ago)
+siva ultimate Dear Siva,thanks a lot for your feedback and for subscribing, please share this video with your peers. Regards
Thales Sehn Körting (3 years ago)
Dear 叶熙泽 Suppose you have 3 variables with the following feature values: x1 = [1, 2, 5, 6] x2 = [4, 2, 7, 9] x3 = [1, 2, 5, 6] x1 and x3 are very correlated (i.e. equal in this case). Then it is not efficient to any algorithm to use both variables, since computations of distances and so on will return equal values. So the proposal here is to use only x1 and x2. Regards
Xize Ye (3 years ago)
Nicely explained! But I still have one question. In transformation process you said "using two correlated variables is useless" I am not sure I understand why? Thanks.
Thales Sehn Körting (1 year ago)
Hi, thanks for your feedback (sorry for the delay to answer) two correlated variables could be interpreted (in the limit) as two identical variables. If your algorithm takes 1 hour to process one variable, it will take 2 hours to get the same result. Regards
Carlos Federico Gaona (3 years ago)
Awesome video..!!  Really elegant and easy to understand. One more subscriber for you.!
Thales Sehn Körting (3 years ago)
Dear Carlos, Thanks for your valuable comments and subscription. Regards
Valerii Potokov (4 years ago)
Great explanation! Thank you!
Hasan Al-Nashash (1 year ago)
Excellent video. Thanks
Valerii Potokov (4 years ago)
Thank you! I've subscribed to your channel. You have very good presentations about interesting subjects.
Thales Sehn Körting (4 years ago)
Dear friend, thanks for your valuable comments. Please subscribe to my channel and share this video with your peers

Would you like to comment?

Join YouTube for a free account, or sign in if you are already a member.