Business Analytics and Big Data [EINGM103]

Learning outcomes

At the end of this course, the student should be able to:

• Remember and understand the different types of business analytics
• Understand the different applications of business analytics
• Apply the analytics process model to various business applications
• Analyze the impact of data preprocessing on the analytical models
• Understand most important concepts descriptive and predictive analytical models
• Analyze and evaluate the different analytical models in a business context
• Understand the basic concepts of text analytics and evaluate there usefulness in a business context

Objectives

Business analytics is defined as an interdisciplinary field of research that lies at the interface of computer science, operations research and data science. The aim of business analytics is to use descriptive, predictive and prescriptive models on big data to increase business performance. Hence, business analytics can give companies a strategic and operational advantage in a big data world.

This course will focus on the different parts of the business analytics process: preprocessing, analytical modelling and post-processing. Special emphasis will be given to specific business applications like customer churn prediction, credit scoring, and fraud detection. After an introduction to the different types of business analytics and its application, the most important big data preprocessing steps and analytical models are explained. Preprocessing will dig deeper into identification, cleaning, selecting and preparing of big data. Next, the most important analytical models are discussed: descriptive and predictive analytics. In descriptive analytics, unsupervised learning methods like association rule mining, dimensionality reduction and clustering are essential methods to understand and describe your data. In predictive analytics, the most important supervised learning models (e.g., linear and logistic regression, decision trees and neural networks) are introduced and their use in specific business application.

Given the rising importance of unstructured data, the course concludes with an introduction to text analytics and natural language processing, again with a special emphasis on how these methods are used in a business context.

Content

1. Introduction to analytics
   • Concepts
   • Definitions
   • Analytics process
   • Business applications
2. Preprocessing
   • Data understanding
   • Data preparation
   • Feature engineering
3. Descriptive analytics
   • Association rule mining
   • Dimensionality reduction
   • Clustering
4. Predictive analytics
   • Linear models
   • Nonlinear models
   • AI models
5. Text mining
   • Concept
   • Bag-of-words and term frequency
   • Word embeddings