Fourth Semester
FRAUD DETECTION
This course introduces the use of analytics to detect fraud in a variety of contexts. This class shows how to use machine learning techniques to detect fraudulent patterns in historical data, and how to predict future occurrences of fraud. Students will learn how to use supervised learning, unsupervised learning, and social network learning for these types of analyses. Students will be introduced to these techniques in the domains of credit card fraud, healthcare fraud, insurance fraud, employee fraud, telecommunications fraud, web click fraud, and others. The course is experiential and will apply concepts taught in prior data wrangling and machine learning courses using real-world data sets and fraud scenarios.
OR
LEGAL ANALYTICS
This course introduces the topic of law as it applies to data science and the data scientist. The law is inextricably intertwined with data science and in very diverse ways. At a high-level, the law impacts data science in three major ways. One, data science greatly facilitates the practice of law as it does many other domains. Second, compliance laws and regulations determine how data science tasks and projects are undertaken. And, third, the law impacts the data scientist in direct and significant ways as a practicing professional. As with most law-school courses, the learning in this course is facilitated by the application of laws to factual scenarios; students will have the opportunity to express their thoughts and to debate underlying issues. Given this, a lab component to this course is not necessary.
DYNAMIC VISUALIZATION
This course introduces advanced visualization techniques for developing dynamic, interactive, and animated data visualization. Students will learn a variety of techniques for the visualization of complicated data sets. These techniques are valuable for visualizing genomic data, social or other complex networks, healthcare data, business dynamics changing over time, weather and scientific data, and others. Often the visual presentation of data is enhanced when it is made interactive and dynamic, allowing users to "move through" the data and manipulate the data graphically for exploratory analysis. This presentation often involves web application development, and students will be exposed to these rudiments as well as tools that enable faster development of data visualization.
CAPSTONE INDUSTRY-SPONSORED PROJECT (THROUGHOUT FOURTH SEMESTER)
This course is a culmination of all modules in the MSc Data Science program. It provides an experiential learning opportunity that connects all of the materials covered in the MSc Data Science program. Students will be formed into teams (typically of three) and assigned to an industry-sponsored project. Capstone projects will be agreed upon in advance with sponsoring companies and will represent real-world business issues that are amenable to an analytic approach. These projects will be conducted in close oversight by the sponsoring company, as well as, a University of the Pacific (UOP) faculty member and may be conducted on the sponsoring company's premises using their preferred systems and tools (at the sponsoring company's discretion).
Students will be expected to complete the specific project outcomes defined at the start of the project, including a final presentation to the sponsoring company, their project lead and executive management, as well as Pacific faculty and program director. The presentation will include a clear explanation of the data sources, data cleanliness / deficiencies, analytic techniques used, derived insights and compelling visualizations and recommendations. The final report should also indicate any known deficiencies in the results (e.g. due to missing data) and the degree of confidence their customers should have in the insights and recommendations provided.
