A guide to machine learning algorithms and their applications

The term machine learning is often incorrectly interchanged with artificial intelligence. Actually, machine learning is a subfield of AI. Machine learning is also sometimes confused with predictive analytics, or predictive modelling. Again, machine learning can be used for predictive modeling but it's just one type of predictive analytics, and its uses are wider than predictive modeling.

Coined by American computer scientist Arthur Samuel in 1959, the term machine learning is defined as a “computer’s ability to learn without being explicitly programmed."

At its most basic, machine learning uses programmed algorithms that receive and analyze input data to predict output values within an acceptable range. As new data is fed to these algorithms, they learn and optimize their operations to improve performance, developing intelligence over time.

There are four types of machine learning algorithms: supervised, semi-supervised, unsupervised and reinforcement. 

Supervised learning

In supervised learning, the machine is taught by example. The operator provides the machine learning algorithm with a known dataset that includes desired inputs and outputs, and the algorithm must find a method to determine how to arrive at those inputs and outputs. While the operator knows the correct answers to the problem, the algorithm identifies patterns in data, learns from observations and makes predictions. The algorithm makes predictions and is corrected by the operator – and this process continues until the algorithm achieves a high level of accuracy/performance.

Under the umbrella of supervised learning fall: classification, regression and forecasting.

1. Classification: In classification tasks, the machine learning program must draw a conclusion from observed values and determine to
   what category new observations belong. For example, when filtering emails as spam or not spam, the program looks at existing observational data and filter the emails accordingly.
2. Regression: In regression tasks, the machine learning program must estimate – and understand – the relationships among variables. Regression analysis focuses on one dependent variable and a series of other changing variables – making it particularly useful for prediction and forecasting.
3. Forecasting: Forecasting is the process of making predictions about the future based on the past and present data, and is commonly used to analyze trends.

Semi-supervised learning

Semi-supervised learning is similar to supervised learning but instead uses both labelled and unlabelled data. Labelled data is essentially information that has meaningful tags so that the algorithm can understand the data, while unlabelled data lacks that information. By combining these techniques, machine learning algorithms can learn to label unlabelled data.

Unsupervised learning

Here, the machine learning algorithm studies data to identify patterns. There is no answer key or human operator to provide instruction. Instead, the machine determines the correlations and relationships by analyzing available data. In an unsupervised learning process, the machine learning algorithm is left to interpret large data sets and address that data accordingly. The algorithm tries to organize that data in some way to describe its structure. This might mean grouping the data into clusters or arranging it in a way that looks more organized.

As it assesses more data, its ability to make decisions on that data gradually improves and becomes more refined.

Unsupervised learning techniques include:

1. Clustering: Clustering involves grouping sets of similar data (based on defined criteria). It’s useful for segmenting data into several groups and performing analysis on each data set to find patterns.
2. Dimension reduction: Dimension reduction reduces the number of variables being considered to find the exact information required.

Reinforcement learning

Reinforcement learning focuses on regimented learning processes, where a machine learning algorithm is provided with a set of actions, parameters and end values. By defining the rules, the machine learning algorithm then tries to explore different options and possibilities, monitoring and evaluating each result to determine which one is optimal. Reinforcement learning teaches the machine trial and error. It learns from past experiences and begins to adapt its approach in response to the situation to achieve the best possible result.

Deciding which machine learning algorithms to use

Choosing the right machine learning algorithm depends on several factors, including, but not limited to: data size, quality and diversity, as well as what answers businesses want to derive from that data. Additional considerations include accuracy, training time, parameters, data points and much more. Therefore, choosing the right algorithm is both a combination of business need, specification, experimentation and time available.

Even the most experienced data scientists cannot tell you which algorithm will perform the best before experimenting with others. We have, however, compiled a machine learning algorithm cheat sheet, which will help you find the most appropriate one for your specific challenges.