1
00:00:01,070 --> 00:00:07,930
They see injuries for regression and classification have a number of advantages over the classical approaches,

2
00:00:08,000 --> 00:00:12,700
such as linear regression, logistic regression or linear discriminant analysis.

3
00:00:14,870 --> 00:00:17,750
Here are some of the advantages of the Henries.

4
00:00:20,160 --> 00:00:22,920
Foster's trees are very easy to explain to people.

5
00:00:23,310 --> 00:00:27,540
In fact, they are even easier to explain than linear regression.

6
00:00:29,140 --> 00:00:35,890
Secondly, some people believe that this country's more closely mirror human decision making, then

7
00:00:36,010 --> 00:00:40,900
regression or classification approaches based on linear regression or logistic regression.

8
00:00:42,910 --> 00:00:49,840
Thirdly, trees can be displayed graphically and are very easily interpreted even by a non expert.

9
00:00:51,340 --> 00:00:58,210
And lastly, trees can easily handle qualitative predictors without the need to create dummy variables.

10
00:00:59,410 --> 00:01:05,350
As for the disadvantages, that is one major disadvantage of a simple importunity entry.

11
00:01:07,150 --> 00:01:14,400
A simple entry generally does not have the same level of predictive accuracy as some of the other regulation

12
00:01:14,400 --> 00:01:15,810
or classification approaches.

13
00:01:17,020 --> 00:01:20,470
But by aggregating many decision trees.

14
00:01:21,440 --> 00:01:27,980
Or what we call as creating ensembles, we can significantly improve the performance of visionary's.

15
00:01:29,360 --> 00:01:32,840
We'll be looking at on sampling techniques in the coming videos.
