Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification...
Transcript of Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification...
![Page 1: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/1.jpg)
1
Apache MADlib (Incubating)
Oct 2016
User Survey Results
![Page 2: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/2.jpg)
2
Received ~40 responses from 27 different companies
![Page 3: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/3.jpg)
3
Summary (1) • ~50% of respondents have 1 year or less of
MADlib use• Fraud detection is the most common use case• Regression (various), clustering and random
forest are the most commonly used MADlib algorithms
• Gradient boosting is the most commonly requested new algorithm
![Page 4: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/4.jpg)
4
Summary (2) • Users prefer new algorithms more than
improvements to existing algorithms by a 2:1 margin
• Improved documentation/examples and better performance are the biggest concerns
• The most common other tools used by respondents are R, Spark and Python (and associated libraries)
![Page 5: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/5.jpg)
5
Q1
![Page 6: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/6.jpg)
6
Q2
![Page 7: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/7.jpg)
7
Q3
![Page 8: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/8.jpg)
8
Q4 - Top Use Cases
![Page 9: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/9.jpg)
9
Q4 - Other Use Cases
![Page 10: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/10.jpg)
10
Q4 - Use Cases
Stemmed, stop words removed
![Page 11: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/11.jpg)
11
Q5 - Frequently Used Algorithms
![Page 12: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/12.jpg)
12
Q6 - Top Requested Features
*Note that there is an R interface called PivotalRhttps://cran.r-project.org/web/packages/PivotalR/
*
![Page 13: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/13.jpg)
13
Q6 - Other Requested Features
*
![Page 14: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/14.jpg)
14
Q6 - Requested Features
All responses, stemmed, stop words removed
![Page 15: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/15.jpg)
15
Q7 - Main Concerns
![Page 16: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/16.jpg)
16
Q7 - Main Concerns
All responses, stemmed, stop words removed
![Page 17: Apache MADlib (Incubating)...Decision tree PCA Low rank matrix factorization Classification (various) PivotalR SVM Count 10 busi center exploratori scienc System intellig histori essenti](https://reader034.fdocuments.in/reader034/viewer/2022051915/6007125d3265834e1f7659fc/html5/thumbnails/17.jpg)
17
Q8 - Other Tools Used
+Several others...