DA 350: Advanced Methods for Data Analytics

This course is designed to develop students’ understanding of the cutting edge methods and algorithms of data analytics and how they can be used to answer questions about real-world problems. These methods, and the underlying models, can be used to learn from existing data to make predictions about new data. The course will examine both supervised and unsupervised methods and will include topics such as clustering, classification, and network analysis.

Prerequisites: CS 181 and MATH 220 or consent of instructor.

Course Goals:

• Apply advanced data analytics methods to solve real world problems

• Generate predictions for classification and regression problems using cutting edge machine learning techniques

• Evaluate the performance of predictions and choose between potential models

• Prescribe actions to take by solving optimization problems with data

• Handle missing data with both simple and sophisticated techniques

• Describe structures in data using unsupervised algorithms

• Reduce dimensionality of data for easier storage, computation, and analysis

• Understand and implement analytics algorithms from primary sources and documentation

• Estimate algorithm run times and efficiently handle large computations

Some sample projects we work on over the course of the semester:

• Clustering Egyptian Hieroglyphics

• Building a movie recommendation system

• Recognizing the genre of music from sound properties

• Creating and evaluating sports betting schemes

• Detecting credit card fraud

• Optimizing the budget of a soup kitchen to feed as many people as possible healthy, nutitious meals

• Optimizing online ad placement with multi-arm bandit algorithms

The syllabus from spring 2019 can be seen here.