The academic catalog is currently being updated for the 2020-21 year. View the Catalog Archive to access the 2019-20 catalog as well as catalogs from previous years.
Roman Yasinovskyy (department head)
Data science is the study of how we extract meaning from data, and in a data driven world, this is an exciting time to seek a degree in this field. Data science is unique in that it combines techniques and theories from many fields including mathematics, computer science, probability and statistics, machine learning, pattern recognition, communication studies, art, and ethics.
The data science major at Luther is designed to provide students with an interest in data science with the technical skills required to enter this field, along with the interdisciplinary breadth required to apply these skills to a particular field.
Required for a major: DS 120, 320, 420; CS 130, 140, and 150; MATH 115 (or equivalent statistics course, such as MATH 215, BIO 256, MGT 150, PSYC 350, or SOC 350) and MATH 327; and 3 Subject Matter courses, 2 of which must be numbered above 200. Senior Project (DS 490; 1 credit hour) is not required if a student completes the Senior Project in another major.
The writing requirement is fulfilled with MATH 327. The speaking requirement is fulfilled in DS 320 and 420. The research requirement is fulfilled in DS 420.
Subject Matter Courses: Subject Matter courses give students the required background in one of the subject matter fields. Below are subject matter course clusters that would focus on the areas where there is an overlap with analytics. Students may also design their own set of preparatory courses in consultation with the Computer Science department head and subject area faculty. The chosen courses must be approved by the head of Computer Science, who may consult with members of other departments as appropriate. Three courses from different departments may be accepted as long as they form a cohesive package. At least two of the three courses must be numbered 200 or above. Some examples of possible packages include, but are not limited to the following:
Biology: BIO 248, 354, and 356
Business Management: MGT 250, 368, and 371
Economics: ECON 130, 333, and 342
Mathematics: MATH 240, 271, and either MATH 322 or 328
No more than two courses counting for another major or minor may be applied to the data science major, including the subject matter courses. For a double major with Computer Science, a student may only count CS 130, 140, and 150 for both.
Required for a minor: DS 120, 320, and 420; CS 130, 140, 150; and MATH 115 (or equivalent statistics course, such as MATH 215, BIO 256, MGT 150, PSYC 350, or SOC 350). There is no requirement for a capstone project, but students are encouraged to incorporate a data science element into their senior project.
Advanced Placement Credit: A student who receives a score of 4 or 5 on the APCS-A exam will receive credit for CS 150. A student who receives a score of 4 or 5 on the AP Statistics exam may receive credit for Math 115.
View program learning goals for an explanation of learning outcomes in Data Science.
An introduction to the discipline of data science through case studies and hands-on experience. Students will see examples of real data science and will gain an understanding of the theory and practice. They will also use simple tools and techniques to begin to understand the complexities of data manipulation, modeling, and visualization.
A tool based approach to data manipulation, modeling, machine learning, and visualization using one or more packages such as matplotlib, pandas, d3.js, scikit-learn. Topics include data extraction, discovery, cleaning, machine learning algorithms, training procedures, prediction, and visualization. Specific application to real data sets in native formatics from actual data sources.
This course looks at the algorithms and techniques used in Machine learning, including simple neural networks, support vector machines, decision trees and clustering techniques. The course takes a top down approach in using the algorithms through common Data Science tools such as Scikit-learn or R. This course will also look at good experimental design for using these tools.