Now we have a good understanding of our own data. We now know the patterns and the relations in our data. But can we use this patterns and relations to make a good predication to the future?

Machine learning is about making predictions.

Machine learning gives computers the ability to learn without being explicitly programmed “Arthur Samuel in 1959”.

Machine learning focuses on the development of computer programs that can change when exposed to new data.

Giving existing and sufficient data, we can apply one or more machine learning algorithm to build a predictive model that has the ability to process new data and give a good predictions.

Why Machine learning?

Building robust experience from existing information.

Automating the business intelligence and extract information from new data.

‘High-value predictions that can guide better decisions and smart actions in real time without human intervention’ (Source: SAS).

What machine learning can do?

Regression

Simplest machine learning task is to predict values given some feature or attributes, for example: pricing prediction given product specifications.

Classification

From image classification in healthcare to text sentiment analysis in Customer Relation Management, machine learning give us the ability to build classification model for any digital contents.

Recommended System

Predict the “rating” or “preference” that a user would give to an item from past behavior.

Anomaly detection

Is the identification of items, events or observations which do not conform to an expected pattern or other items in a dataset, Typically the anomalous items will translate to some kind of problem such as bank fraud, a structural defect, medical problems or errors in a text.

Advances In machine learning.

With the availability of large amount of data and fast computers hardware.

The machine learning algorithms become applicable.

The current advances in machine learning appear in fields like computer vision, speech recognitions, and Natural language analysis that make virtual assistant like Apple’s Siri possible.

And With Deep learning technologies machine learning become more and more robust and available.

Deep learning save time and effort in feature engineering required for machine learning.

Now computers can extract the meaningful features from any type of data by itself using the same Deep learning algorithm.