BUS 628: Applications in Artificial Intelligence and Machine Learning 

This course covers key concepts and methods in artificial intelligence and machine learning. Students will build on concepts studied in MGMT 433, MGMT 480, and BUS 605, including supervised, unsupervised, and reinforcement learning. The advanced concepts in this class will focus on deep neural networks. These concepts will be applied in finance using the R, SAS, and Python software, with emphasis on risk management, fraud detection, and portfolio optimization. If time permits, we will discuss some shallow learning techniques such as support vector machines. Hidden Markov Models (HMMs) and radial basis function networks will also be discussed, contingent upon time. 

At the end of the course, students should be able to: 

1. Demonstrate a theoretical and practical understanding of the covered machine learning methods

2. Implement these algorithms in R and SAS to analyze business data under alternative scenarios

3. Integrate Python into R using the reticulate package

4. Understand the link between artificial intelligence and machine learning 

5. Distinguish between supervised, unsupervised, and reinforcement learning

6. Understand how to apply these learning algorithms to solve business challenges

7. Evaluate and quantify the predictive performance of learning algorithms

The syllabus is found here.