Advanced Data Science Applications in Fi

The Advanced Data Science Applications in Finance and Insurance course covers topics in database navigation, select advanced predictive analytics models and model interpretability. Topics include relational databases, generalized additive models, deep learning models, linear mixed models, Bayesian approaches, and interpretable machine learning.

Course discussions help students develop an understanding of the models and methodologies, as well as the ability to implement these models in R or python using opensource packages. Course assignments help students practice applying these models to financial, insurance and other data, as well as gain additional insights through validating aspects of the models. After taking this course, students will be able to apply these advanced predictive analytics models to financial and insurance data to better inform data-driven decision making by combining their theoretical understanding, domain knowledge and coding skills.

Some topics covered are relevant to the Advanced Topics in Predictive Analytics (ATPA) exam of the Society of Actuaries, and (with a more analytical emphasis) to the quantitative methods section of the CFA Program Level II exam by the CFA Institute.

Familiarity with machine learning models covered in the Data Science in Finance and Insurance course is helpful. Prior exposure to linear algebra, calculus, statistics, and a working knowledge of python, R and spreadsheets are necessary.