Machine Learning Introduction

Welcome to the Machine learning Introduction, where you will learn both the concept behind the Machine Learning(ML) model as well as its implementation of it in Python.

My name is Jagdish Chavan as a working Data Scientist and Industry Trainer, my Courses have been enrolled by over 1000 + students holding B.Sc in Computer Science with Mathematics and Statistics and I have experience in Building Projects in Data Science, ML, DL application and the consulting industry.

While doing my Job, I realized That many Data Scientists and beginners in data analytics are overwhelmed by Machine Learning. This article and coming articles focus will be on students who want to expand their skill set with this unconventional machine learning technique.

A practising data scientist needs to know from concept to code without getting too much mathematical about it. if you regularly put one hour a day within a week, you will be able to make ML models and answer ML-related interview questions.

Every data practitioner has an idea of what Machine Learning is you must have heard of it or read about it. But if you are not clear that what it really is, or you know about it in bits and pieces, this section should help you put things in perspective and build some intuition around it. so lets us answer the question.

What is Machine Learning?

Machine learning is programming computers to optimize a performance criterion using example data or past experience. Machine learning can automatically detect patterns in data, and then use the uncovered patterns to predict future data or other outcomes of interest.

Why Machine Learning?

Machine learning based on statistics is basically attempting to find the relationship between input and output variables

• Organizations/governments are collecting a lot of data
• Information from data is being used to take a key business/political decisions.
• At lower levels in organization, data is used for MIS reporting
• At higher levels, data based on prescriptive and predictive models are being built.
• Machine learning is the most popular technique for creating these predictive and prescriptive models.

There are a few terms which are being used interchangeably these days. However, they have a minute difference between them

Machine Learning Vs statistics

• Traditional Statistics focuses on provable results with mathematical assumptions, and care less about computation.
• Statistics: A useful tool for Machine Learning.

Machine Learning Vs. Artificial Intelligence

• Machine Learning is one possible route to realising AI

Machine Learning Vs. Data Mining

• Traditional DM focuses on provable results with math assumptions along with efficient computation in large datasets.
• Difficult to distinguish between ML and DM reality.

Example

Machine learning based on statisticsis basically attempting to find the relationship between input and output variables.

• Paypal uses Macine Learning to detect fraud
• Google is able to predict what we want to search bases what people around us are searching or basses our search history and numerous other predictors.

There are severalother use cases of machine learning, which can be categorised as the industry in

Banking/telecom and retail sector, companies are using machine learning to identify the

• prospective customers
• Dissatisfied customers
• Good customers, bad payers.

Obtain

• More effective advertising
• Less credit risk
• Fewer fraud
• Decreased churn rate

Biomedical/Biometrics

Medicine

• Screening
• Diagnosis and prognosis
• Drug discovery

Security

• Face recognition
• Signature/fingerprint/iris vrification
• DNA fingerprinting

Computer/Internet

Computer Interfaces

• Troubleshooting wizards
• Handwriting and speech
• Chat bots

Internet

• Hit ranking
• Spam filtering
• Text categorization
• Text translation
• Recommendation

Example

A real estate agent who wants to price a particular property will have:

• Output variable:Price of property(Y)
• Input variable:Area covered(X1), Number of bedrooms(X2), proximity to a landmark(X3), proximity to market(X4), recent sale price of a neighborhood property (X5) and so on
• The real estate wants to find out Y=f(X1,X2,X3,X4,X5....)
• So that whenever developer gives a value of the input variable to this function's developer can get the price of the property.

Why Estimate f(X)

• f(X) defines the relationship between dependent and independent variable
• Prediction: When the value of input variable is available and output variable is to be predicted. we are only interested in the value of Y, not in the relationship of Y with other variables.
• Inference:When the relationship between input and output variable is important. we want to establish how output variable with change in each predictor variable.

Choice of model for estimating will depend on whether we want to predict or infer.

• For Prediction, accuracy of predicted function is the most important.
• For Inference, interpretability of predicted function is most important

For example, Linear regression is simple to interpret but may not give very accurate predictedvalues of Y

whereas highly non-linear models may be predicting very accurately but the relationship may be very difficult to interpret.

How To Estimate F(X)

Next, we need to specify the type of learning method.

Finally, one request if you really like what you read and acquire knowledge about feel free to share the article with your Friends, Colleagues, students or anyone you might think will benefit from this. sharing is caring.