Course offerings reflect the 2020-2021 Elmhurst University Catalog. One unit of credit equals four semester hours.
Topics include an integrated and detailed comparison of relational, hierarchical and network database systems. Database design and physical storage requirements, including distributed database design and related management issues, are discussed. High-level query languages using artificial intelligence techniques are reviewed along with other topics such as database compression, encryption and security.
Business intelligence represents a conceptual framework for decision support. It combines analytics, data warehouses, applications and methodologies to facilitate the transformation of data into meaningful and functional information. The major objective of business intelligence is to enhance the decision-making process at all levels of management. Data mining is a process that utilizes statistical analysis, probability theory, mathematical modeling, artificial intelligence and machine learning techniques to extract useful information and subsequent knowledge from large data repositories, commonly referred to as “big data.” This course examines a number of emerging methods proven to be of value in recognizing patterns and making predictions from an applications perspective. Students will be provided the opportunity for hands-on experimentation using software and case studies.
This course covers the application of appropriate high-level programming languages for expressing software design patterns used for extracting and processing big data within the Hadoop environment. These high-level languages include imperative, object-oriented languages such as PIG, HIVE and Scala. Examples will also be presented in Java and Python. The languages will be presented in support of big data processing relying on the map-reduce paradigm. Additional libraries will be explored in order to support activities of data mining as well as machine learning.
The ability to move data along the continuum from information to insight to action requires a strong foundation of skills in various quantitative methods. This course begins with a systematic and integrated overview of concepts from probability theory, statistics and mathematical modeling such as probability distributions, cumulative probability distributions, descriptive statistics, hypothesis testing, correlation analysis, linear regression, multivariate regression and mathematical model design. The course then proceeds to examine modern tools for conducting analyses using these quantitative methods on both small-scale and large-scale datasets. Case studies from a variety of settings are used to develop students’ abilities to successfully apply the techniques learned in this course to practical circumstances that often, because of the ambiguities involved, present limitations to the power of these mathematical tools. Topics from this course also provide the foundation for some subjects covered in the analytical methods course and the data mining and business intelligence course.
Each student completes a project incorporating the practical application of several of the program’s data mining techniques to one or more data sets chosen by the student or provided by the instructor. In addition to the correct use of the techniques and interpretation of the results, emphasis is placed on the student’s ability to gauge the resultant impact on the organization’s business intelligence processes and procedures. Prior to the submission of the final project, students submit a proposal describing the application and the data mining tools to be utilized.
This course builds upon the foundation established in the quantitative methods course to develop the advanced analytical methods required for in-depth applications of data science. Topics covered include advanced techniques in statistics and predictive modeling such as feature engineering, variations of multilinear and logistic regression, principal component analysis, advanced approaches to clustering and segmentation, time series forecasting, and biological methods such as neural networks and genetic algorithms. Course topics will be introduced from both a theoretical framework and through the use of case studies in applied settings.
This course provides a business-oriented framework for the data scientist to identify, prioritize and perform data analytical projects that drive business value and enhance competitive advantage. The course examines the data ecosystem, both external and internal to the enterprise, as well as business processes and networks upon which analytical projects can be used to reduce organizational risk and drive the creation of economic value. Topics covered include: marketing, sales and customer data exploration, supply chain data exploration, operations data exploration, financial data exploration and project management methods to convert information gain into business value. A variety of business process data sets will be examined using analytical tools. Students will conduct the steps of an analytical workflow on a selected business process and create a project plan to drive value.
In this course, students learn to apply Enterprise Project Management (EPM) concepts as applied to the development, deployment and value attainment of Business Intelligence projects. The course provides a hands-on experience where students successfully manage the implementation/deployment life cycle of data-oriented projects in order to achieve a business process transformation. Special emphasis is placed upon value mapping, cross-functional collaboration, risk management at the project-program-portfolio levels, organizational change management, stakeholder management and business value attainment. The course is highly interactive as students complete project management assignments working individually and in teams using collaboration software.
Prerequisites: MDS 546, MDS 534, MPM 501, MPM 502. Students who are certified project management professionals or who have prior equivalent experience may waive the project management course requirements.
In this course, the student learns to apply the project management tools and techniques needed to effectively plan and lead project teams on a business transformation initiative. The course emphasizes project execution by providing the student with a hands-on, team experience in developing, training, validating and deploying machine learning and time series models to a web production environment. Students construct KPI dashboards and learn methods of organizational change management necessary to drive business value creation across a variety of common enterprise processes including marketing/sales, operations, procurement, finance and customer service. The course is highly interactive as students complete data science and project management assignments working individually as well as in teams using collaboration software.
Prerequisite: MDS 561.
This course emphasizes the application of the primary topics covered in MDS 534 Data Mining and Business Intelligence and MDS 556 Analytical Methods within large case studies while learning to choose the appropriate programming language(s), software design pattern(s) and/or software tools, which are covered in CS 535 Programming Models and Environments. In these case studies students utilize data mining tools where appropriate and utilize advanced techniques in statistics and mathematical modeling for supporting conclusions and decisions. Students utilize software tools to visually present conclusions and decisions. Case studies are chosen from a wide spectrum of problem domains.
This course provides opportunities for students to study specialized topics in data science. Examples include time series forecasting and data science applications of linear algebra.
This course serves as the capstone for the program. Students will apply concepts learned and skills developed in the other required courses to complete a major project that demonstrates the full range of their data science knowledge and capabilities.
This course is the first of two courses required to complete a thesis option in the master’s program in data science.
This course is the second of two courses required to complete a thesis option in the master’s program in data science.
Students must complete two graduate-level electives at Elmhurst.