Theory

Music recommending model using Python and Machine Learning

Machine Learning is the field of scientific study of statistical models and algorithms that gives computers the capability to learn without being explicitly programmed (Sameul, 2010). Machine learning helps in making better predication and decisions with minimal human intervention as it generates insight by identifying the natural patterns in data with Machine Learning algorithms. Machine Learning automates analytical model building as it is a method of data analysis and a branch of Artificial Intelligence.

Why Machine Learning is Important?

Machine Learning saves time and automates the processes by which humans can concentrate their energy and time on making more complex decision. Machine Learning has a high importance as the predictions made by it can guide to take smart actions and make better decisions without the help of human. Machine Learning have replaced traditional statistical techniques by automating the interpretation and extraction works which helps in analyzing the large chunks of data by involving automatic sets of generic methods. The value of Machine Learning Technology is realized by the most company which is working with large amounts of data. Some of the areas where Machine Learning plays a vital role are in financial services, government, healthcare, retail, oil and gas, transportation etc. Machine Learning has also other applications in self-driving cars, Robotics, Language Processing, Vision Processing, Forecasting Stock Market Trends, weather and games and so on.

Machine Learning Methods

 Supervised learning is a machine learning method that are designed to learn by example. It is called supervised learning as the name in indicates the presence of a supervisor as a teacher. A supervised learning algorithm takes a known set of input dataset and its known responses to the output data to learn classification or regression model. A learning algorithm then trains a model to generate a prediction for the response to new data or the test dataset (Gangadhar Shobha, 2018). The two important techniques in supervised learning are:

Regression: This technique predicts continuous responses.

Classification: Classification task predicts discrete responses. It is the technique of categorizing the observation into different category. In other words, the data is analyzed and based on some condition it is divided in various category. There are different types of Classification like Decision Tree, Random Forest, Naïve Bayes, KNN, logistic regression, linear regression etc. we are going use decision tree for this project.

‘A decision tree is a graphical representation of all the possible solutions to a decision based on certain conditions.’ This is called decision tree because it starts with a root and then branches off to a number of solutions just like a tree. Even a tree starts from a root and it starts growing its branches once it gets bigger just like in decision tree it has a root which keeps on growing with increasing number of decision and conditions. A decision tree is a predictor, h: X → Y, that predicts the label associated with an instance x by traveling from a root node of a tree to a leaf. For simplicity we focus on the binary classification setting, namely, Y = {0, 1}, but decision trees can be applied for other prediction problems as well (Shalev-Shwartz, 2014). The main components of decision tree in building a model are splitting, stopping and pruning. The figure below illustrates a simple decision tree model that includes two continuous variables, x1 and x2 ranging from 0 to 1 and a single binary target variable Y (0 or 1).