4 Types of Data Analytics - A Quick View
3 Video ViewsยทOct 9, 2024
Here you go, a quick note on the 4 types of data analytics
Hello friends, welcome back.
In this session, we'll understand what are the four types of data analytics that are
available.
We are going to discuss the four types of data analytics, the difference, the tools
connected to it in a very crispy session, not more than five to seven minutes is what
I need.
And this could be a very good session for you to understand the types and the classifications.
Let's go ahead with the first one.
Descriptive data analytics is the first step.
The term descriptive tells you that it is all about what, remember descriptive data
analytics is all about what, what's happening in your business, what has happened, this
can be done with the live data and this helps in visualization.
This tells what has happened to understand it is all about past.
So, I am going to analyze a set of data, I'm going to understand a set of data and I will
understand what's happening in your business.
That's called descriptive analytics.
Second is diagnostic.
Next to what is why?
Something has happened, but why that has happened is the point that we need to understand.
Something has happened, we need to go into the root cause of that.
Why is it happening?
Let's diagnose.
This helps in understanding the root of the problem.
For example, you are going to a doctor, you've got a headache, so what has happened, headache
has come.
So, what is the root cause?
We need to understand that.
So, what and why?
So, the root cause is to be diagnosed and that's called diagnostic data analytics.
The first one will tell you what, the second one will tell you why.
The third one is predictive.
Well, what might happen if a condition occurs?
What might happen if this particular condition occurs tomorrow?
So, prediction is going to help you in understanding the future.
History will also be considered towards understanding what is going to happen tomorrow.
So, first one is what, second one is why, third one is if.
So, what has happened, why it has happened, if this happens, what will happen?
So, this is called predictive data analytics.
And finally, it comes as prospective data analytics.
What is it?
Recommendation.
Very simple.
What should I do?
I have got a set of data, I analyze, now what should I do to meet the requirements in the
future?
I wish I want to become this, so what should I do to become this?
That's it.
What are the recommendations that are available for me to do that?
That's it.
So, the first one says what, second one says why, third one says if and the fourth one
are recommendations.
As you can see, the value and the complexity increases as the growth happens from the descriptive
towards prospective.
Descriptive is simple, it goes slightly complex in diagnostic, predictive is tougher and prospective
is what is very difficult.
You need to go with more challenges when you come to predictive data analytics.
Now, we need to understand one more thing very quickly.
So, descriptive talks about the past.
Diagnostic, it's all about the past again.
Predictive and if you see prospective, they both are talking about future.
So, if you want to understand how, what you have done, you need to go ahead with the past
analytics, but what you need to do, how do you need to do is going to be future analytics.
That's what we are presenting here as a very neat presentation.
And tools and techniques are available for you to accomplish these kind of targets.
Descriptive analytics can be done with metrics and statistics.
The diagnostic analytics can be done with PC and regression analytics kind of stuff.
The predictive analytics can be done with machine learning algorithms and prospective
analytics can be done with neural networks and recommender systems which are available
in the market.
I hope it was useful.
This is a very short session, but I hope you have understood the types of data analytics.
Thank you very much for following my channel and the content.
If you like the channel and the content, give a thumbs up and subscribe please.
Thank you.

