Gain an Understanding of Predictive Analytics Methods

University of North Carolina Wilmington (UNCW) students who complete the Master of Science in Business Analytics online program become skilled in analyzing data, building models, and generating impactful data visualizations through their study of common predictive analytics techniques such as: regression, classification and regression trees, random forests, and neural networks.

Learning about these techniques, understanding them and being able to use them efficiently is important in today's competitive global business world. Company managers and executives consider some type of predictive forecast in almost every decision they make. Being able to rely on sound predictions about trends and demands of clients and consumers is a necessity.

Preparing Students for Success

Students in UNCW's M.S. in Business Analytics program will study the following predictive analytics methods:

Regression is a statistical modeling approach that is used to examine between predictor and response variables. Applications of regression techniques are wide-ranging. For example, a company may use regression to predict future demand for a product. A marketing professional may use regression to estimate the likelihood that a customer will respond to an advertisement. Understanding regression sets the stage for exploring more advanced and powerful predictive techniques.

Classification and regression trees are predictive analytics tools that use a tree-like model to develop predictions. Such trees are highly-intuitive, easy to visualize, and can often replicate the processes that humans use to make decisions. The random forest technique can then be used to leverage the power of classification or regression trees to further improve predictive accuracy.

Neural networks are a type of machine learning known as unsupervised learning. Neural networks and related techniques such as deep learning can uncover hidden relationships within data that can then be used to develop powerful insights. Many modern predictive applications such as image recognition often rely on the power of neural networks.

These and other predictive analytics techniques are vitally important if businesses, corporations and other entities are going to cope with challenges such as sudden changes in customer demand levels, price-cutting maneuvers by competitors, and large swings in the economy. Predictive analytics gives business executives and managers the information they need to address these issues and others effectively.

A number of predictive analytics techniques have been developed in recent years to deal with the increasing variety and complexity of managerial forecasting challenges. Each predictive analytics method has its special use, and users must be certain they have chosen the right technique to address their particular situation. The M.S. in Business Analytics program at UNCW is equipping students with the kind of knowledge and expertise that companies demand — and will continue to demand — in response to the growing need for predictive analytics.

Have a question or concern about this article? Please contact us.