1
00:00:00,060 --> 00:00:05,340
Hello, everyone, welcome to this online session on exploratory data analysis.

2
00:00:06,150 --> 00:00:12,990
Before you develop artificial intelligence machine learning model, you are expected to do some data

3
00:00:12,990 --> 00:00:13,820
analysis.

4
00:00:14,430 --> 00:00:16,530
You are expected to check a few things.

5
00:00:17,370 --> 00:00:21,260
All these things are done to ensure a higher forecast accuracy.

6
00:00:21,900 --> 00:00:29,040
I'm bringing decision based on my personal experience in doing exploratory data analysis and in trying

7
00:00:29,040 --> 00:00:32,780
to improve the forecast accuracy of machine learning models.

8
00:00:33,600 --> 00:00:39,930
I'm confident that this session will be very useful to young learners and also to young professionals,

9
00:00:40,290 --> 00:00:47,130
because I have seen that young professionals have a tendency to jump straight into developing artificial

10
00:00:47,130 --> 00:00:52,330
intelligence machine learning models without doing this exploratory data analysis.

11
00:00:52,860 --> 00:00:58,140
So this session will talk about one of the things you need to do before you build the models.

12
00:00:58,770 --> 00:01:05,220
How can you understand the data better and what are the things you need to check as part of this exploratory

13
00:01:05,220 --> 00:01:06,150
data analytics?

14
00:01:06,450 --> 00:01:09,000
MultiKulti is one of those checks.

15
00:01:09,690 --> 00:01:14,370
So we going to start with understanding the data and univariate analysis.

16
00:01:14,370 --> 00:01:20,880
And by varied analysis, how can you do this right as part of exploratory data analysis, if there are

17
00:01:20,880 --> 00:01:22,760
missing values, how are you going to handle it?

18
00:01:23,070 --> 00:01:26,960
Because in real life scenario, you are going to have missing values, right?

19
00:01:27,930 --> 00:01:29,170
That's that's part of life.

20
00:01:29,520 --> 00:01:34,310
So how are you going to handle and you will have outlines in such a scenario?

21
00:01:34,800 --> 00:01:37,500
How are you going to manage the outlets?

22
00:01:37,770 --> 00:01:38,100
Right.

23
00:01:38,520 --> 00:01:41,790
Do you need to transform the variables or do you need to do something more?

24
00:01:42,210 --> 00:01:45,570
All of this we will be covering as part of it.

25
00:01:46,470 --> 00:01:54,900
OK, so before winding up the introductory session, I want to take a minute to introduce myself.

26
00:01:56,040 --> 00:02:02,190
I'm the founder and CEO of an artificial intelligence helps people that I have about two decades of

27
00:02:02,190 --> 00:02:07,010
experience, predominantly in the tech and related fields.

28
00:02:07,980 --> 00:02:15,370
I have developed products in the areas of health care Industry 4.0 and risk and customer experience.

29
00:02:15,840 --> 00:02:17,160
I'm also an author.

30
00:02:17,400 --> 00:02:23,040
I have numerous certifications in the areas of artificial intelligence, Six Sigma Project Management

31
00:02:23,220 --> 00:02:24,030
and LP.

32
00:02:24,870 --> 00:02:31,580
I won global awards in the areas of high quality customer experience and leadership excellence.

33
00:02:32,040 --> 00:02:33,060
So that's about me.

34
00:02:33,330 --> 00:02:34,400
And let's get started.
