Data Science and Artificial Intelligence

Predictive Analytics for Business Applications

Seminar, 2.00 ECTS

 

Course content

In the course of this seminar, relevant methods of predicitive analysis in the context of the relevant business application are studied. Use cases will be utilized to practice data preprocessing techniques as well as model tuning and sampling / resampling. Well-known regression models are studied in the context of concrete business cases. Classification Models (Decision Trees, Rule Induction, K-Nearest Neigbours, Naive Bayesian, Neural Networks, Support Vector Machines, Ensemble Learners, Classification Trees, Rule Based Models) and Methods of Machine Learning (Information Based Learning, Similarity Based Learning, Probability Based Learning , Error Based Learning) are presented in an application-oriented way. Finally, the topics Model Evaluation and Time Series Forecasting are studied.

Learning outcomes

The graduate is able to put predictive analytics into practice for a variety of business applications. They master the practical use of all necessary tools and can weigh the advantages and weaknesses of the individual tools.

Recommended or required reading and other learning resources / tools

Books: Vijay Kotu: Predictive Analytics and Data Mining, Max Kuhn: Applied Predictive Modeling, Daniel Covington: Analytics: Data Sicence, Data Analysis and Predictive Analytics for Business, John D. Kelleher: Fundamentals of Machine Learning for Predicitive Data Analyitcs: Algorithms, Worked Examples and Case Studies, Steven Finlay: Predictive Analytics, Data mining and Big Data
Journals:

Mode of delivery

2 THW Seminar

Prerequisites and co-requisites

Modules MAT 2 and AI 2

Assessment methods and criteria

Continuous appraisal