Machine Learning Introduction - By Saurabh

Here we are going to discuss about the base level concept of the machine learning.

There are numerous algorithms in Machine Learning But,

Linear regression is the oldest ,simplest and widely used supervised learning algorithm for predictive analysis.

What is Linear Regression?

It’s a method to predict a target variable by fitting the best linear relationship between the dependent and independent variable.

Application in Real Life:-

Say you are planning a Trip to Goa with 2 best buddies.You start off in Mumbai and you know its 12 hr drive. While your friends  are in charge of the party operations you're in charge of the logistics involved. You've to plan :the schedule,when to stop and where ,make sure you reach on time ,etc

So,Whats the first thing you do?? Bring a sheet of paper and start your plan!! 

First item in your checklist is Budget.  Its a 12 hr drive -approximately 600 km. the fun ride ,so it should take a total of 15 hrs on the road.

The next question will be "How much money should i allocate for diesel"So you think there must be way to estimate the amount of money needed ,based on the distance you're travelling.

Lets just say youve smartly stored some data of your trips from last year in your excel spreadsheet.

Looking at numbers might not ring any bells ,but it will be way better if you'll have a glance at scatter-plot.

With this plotted graph its clear that there is some connection between how far you can drive without filling the tank.

Now what you want is...

If I drive 600 kms how much will i have to pay for the Diesel??

In Order to answer this question ,you'll have to use the collected data so far and use it predict how much you are going to spend.The idea is that you can make estimated guesses about the future -your trip to Goa - based on data from the past -the data points you've been laboriously logging.

You end up with a mathematical model that describes the relationship between kms driven and money spent to fill the tank.

Once that model is defined, you can provide it with new information - how many miles you're driving from Pune to Goa- and the model will predict how much money you're going to need.

The model will use data from the past to learn what's the relationship between the total of Kms driven and the total amount paid for diesel.

The best way to describe the relationship in Lehman Terms is to show to plot like this.

Clearly there is a linear relationship between Kilometers driven and total paid for diesel Because this relationship is linear, if you spend less money you'll be able to drive fewer kms and if you spend more money you'll be able to drive more kms

And because that relationship is linear and you know how long is your drive from Mumbai to Goa, using a linear model will help you predict how much you are going to budget for diesel.

Next time you find yourself in a situation where you need to estimate a quantity based on a number of factors that can be described by a straight line- you know you can use a Linear Regression.

That's it for this Blog ,I will Explain the components of Linear Regression Model and Display a hands on a Dateset. on the next one..

Thanks for Reading....