Masters in Predictive Analytics | MS Analytics Degree | Northwestern SPS - Northwestern School of Professional Studies

Students learn techniques for building and interpreting mathematical models of real-world phenomena in and across multiple disciplines, including matrices, linear programming, probability, and both differential and integral calculus, with an emphasis on applications. This is for students who want a firm understanding and/or review of these fields of mathematics prior to applying them in subsequent courses. Counts as an elective for students admitted prior to fall 2014. Required as a core course for students admitted for fall 2014 and after.

Students learn to apply statistical techniques to the processing and interpretation of data from various industries and disciplines. Topics covered include probability, descriptive statistics, study design and linear regression. Emphasis will be placed on the application of the data across these industries and disciplines and serve as a core thought process through the entire Predictive Analytics curriculum.

Prerequisite: PREDICT 400-DL Math for Modelers.

This course introduces the field of predictive analytics, which combines business strategy, information technology, and modeling methods. The course reviews the benefits and opportunities of data science, organizational and implementation issues, ethical, regulatory, and compliance issues. It discusses business problems and solutions regarding traditional and contemporary data management systems and the selection of appropriate tools for data collection and analysis. It reviews approaches to business research, sampling, and survey design.

This course develops the foundations of predictive modeling by: introducing the conceptual foundations of regression and multivariate analysis; developing statistical modeling as a process that includes exploratory data analysis, model identification, and model validation; and discussing the difference between the uses of statistical models for statistical inference versus predictive modeling. The high level topics covered in the course include: exploratory data analysis, statistical graphics, linear regression, automated variable selection, principal components analysis, exploratory factor analysis, and cluster analysis. In addition students will be introduced to the SAS statistical software, and its use in data management and statistical modeling.

WINTER 2018 COURSE-SPECIFIC LANGUAGES:

SECTIONS 55, 56 - R

SECTIONS 57 - PYTHON

SECTION 58 - SAS

Prerequisite: PREDICT 401-DL Introduction to Statistical Analysis.

This course extends linear “OLS” regression by introducing the concept of Generalized Linear Model “GLM” regression. The course reviews traditional linear regression as a special case of GLM's, and then continues with logistic regression, poisson regression, and survival analysis. The course is heavily weighted towards practical application with large data sets containing missing values and outliers. It addresses issues of data preparation, model development, model validation, and model deployment.

WINTER 2018 COURSE-SPECIFIC LANGUAGES:

SECTIONS 55, 56 - R

SECTIONS 57 - PYTHON

SECTION 58 - SAS

Prerequisite: PREDICT 410-DL Regression and Multivariate Analysis.

The objective of this course is to cover key analytical techniques used in the analysis and forecasting of time series data. Specific topics include the role of forecasting in organizations, exponential smoothing methods, stationary and non-stationary time series, autocorrelation and partial autocorrelation functions, Univariate ARIMA models, seasonal models, Box-Jenkins methodology, Regression Models with ARIMA errors, Transfer Function modeling, Intervention Analysis, and multivariate time series analysis.

Prerequisite: PREDICT 411-DL Generalized Linear Models.

Behind every analytics project is an analytical data source. In this course, students explore the fundamentals of data management and data preparation. Students acquire hands-on experience with various data file formats, working with quantitative data and text, relational (SQL) database systems, and NoSQL database systems. They access, organize, clean, prepare, transform, and explore data, using database shells, query and scripting languages, and analytical software. This is a case-study- and project-based course with a strong programming component.

The rapid advancement of computational methods from machine/statistical learning, data mining and pattern recognition provides unprecedented opportunities for understanding large, complex datasets. This course takes a practical approach to introduce several machine learning methods with business applications in marketing, finance, and other areas. The course aims to provide a practical survey of modern machine learning techniques that can be applied to make informed business decisions: regression and classification methods, resampling methods and model selection, regularization, perceptron and artificial neural networks, tree-based methods, support vector machines and kernel methods, principal components analysis, and clustering methods. At the end of this course, students will have a basic understanding of how each of these methods learn from data to find underlying patterns useful for prediction, classification, and exploratory data analysis. Further, each student will learn how to implement machine learning methods in the R statistical programming language for improved decision-making in real business situations. The course format is a combination of textbook readings and lecture slides, R Lab video sessions, and group discussions. Weekly quizzes and programming assignments using R will be used to reinforce both machine learning concepts and practice. The final project will involve students applying multiple machine learning methods to solve a practical business problem in marketing

NOTE: Section 57 will be taught in Python.

 Prerequisite: PREDICT 401-DL Introduction to Statistical Analysis.

This course introduces best practices in project management, covering the full project life cycle with a focus on globally accepted standards. It reviews traditional methods, including: integration, portfolio and stakeholder management, chartering, scope definition, estimating, the Delphi method and project evaluation and review technique, precedence diagramming and the critical path method, scheduling, risk analysis and management, resource loading and leveling, Gantt charts, earned value analysis and performance indices of project cost/schedule control systems criteria. It shows how the project management maturity model, leadership, team development, and principles of negotiation apply to organizations of various types: hierarchical and matrix organizations, international teams, and virtual teams. Options on Agile and MS Project are included. Using methods and models from this course, predictive analytics managers should experience greater project definition and structure and be able to execute projects more effectively.

The purpose of this course is to introduce the fundamental leadership theory and associated behaviors that enable students to excel in their analytics careers and to apply these behaviors to personal and professional success. The course builds from the basic premise that leadership is learned. It examines the theory and practice of leadership at the individual and organizational levels, and specifically how to drive effective change management in enterprises at various stages in an enterprise analytics transformation process. Students will be introduced to three weeks of analytics-specific project management, where they will design an analytics project plan using an agile approach incorporating CRISP-DM methodology, and execute that plan in a simulated business setting. Leadership challenges unique to analytics departments in various company sizes will be addressed through the use of case studies and theory-based assignments. The course will focus on developing effective communication strategies and presentations that resonate across business and technical teams.

The capstone course focuses upon the practice of predictive analytics. This course is the culmination of the predictive analytics program. It gives students an opportunity to demonstrate their business strategic thinking, communication, and consulting skills. Business cases across various industries and application areas illustrate strategic advantages of analytics, as well as organizational issues in implementing systems for predictive analytics. Students work in project teams, generating business plans and project implementation plans. Students may choose this course or the master's thesis to fulfill their capstone requirement.

Prerequisite: Students may take one other course simultaenously with PREDICT 498-DL but must complete all other program requirements prior to commencement of the course.

This final project is meant to represent the culmination of students’ experience in the program and must demonstrate mastery of the curriculum and ability to conduct sustained independent research and analysis. The project may be applied or may be a traditional scholarly paper, in both cases a write-up following the paper’s program-specific guidelines is required. Students must submit a proposal and secure a first reader in order to register; for further details students are advised to review the student handbook and contact their academic advisor.

This course provides a comprehensive review of predictive analytics as it relates to marketing management and business strategy. The course gives students an opportunity to work with data relating to customer demographics, marketing communications, and purchasing behavior. Students perform data cleansing, aggregation, and analysis, exploring alternative segmentation schemes for targeted marketing. They design tools for reporting research results to management, including information about consumer purchasing behavior and the effectiveness of marketing campaigns. Conjoint analysis and choice studies are introduced as tools for consumer preference measurement, product design, and pricing research. The course also reviews methods for product positioning and brand equity assessment. This is a case-study- and project-based course involving extensive data analysis.

Prerequisite: PREDICT 411-DL Generalized Linear Models.

Building upon probability theory and inferential statistics, this course provides an introduction to risk analytics. Examples from economics and finance show how to incorporate risk within regression and time series models. Monte Carlo simulation is used to demonstrate how variability in data affects uncertainty about model parameters. Additional topics include subjectivity in risk analysis, causal modeling, stochastic optimization, portfolio analysis, and risk model evaluation.

Prerequisite: PREDICT 411-DL Generalized Linear Models

Recommended: PREDICT 413-DL Time Series Analytics and Forecasting

This course prepares students for establishing and running a data sciences oriented entrepreneurial organization. Topics include evaluating preparedness for entrepreneurial work, activities that would help transform an idea into a running organization, identifying right data, analytics tools, and resources platform, and aligning with unmet market demands. We spend time on growing network of people and assets to leverage, creating innovative intellectual property and sharpening unique competitiveness, making a choice on product development vs. consulting and solution development, and how to leverage marketing channels for sales activities. The key outcome of this course is putting together a business plan. Students working on their visionary entrepreneurial works will complete the course with a comprehensive set of tools and a business plan/pitch for starting an entrepreneurial organization, or create an entrepreneurial approach to utilizing data and analytics in their current job.

Prerequisite: PREDICT 401 Introduction to Statistical Analysis.

Analytics consulting brings together consultative processes and tools for creating a trusted advisor relationship with clients. This course will cover concepts, processes, tools, and techniques for developing consulting proposals, selling, contracting, bringing together teams and resources, servicing, managing projects, and creating recommendation plans. In the process, we will also cover requirements gathering and data gathering, managing client engagement, and client relationship, using high performance measures and project management tools. Finally, we will also cover ethical issues and career challenges.

Prerequisites: PREDICT 401-DL Introduction to Statistical Analysis.

EXPERIMENTAL DESIGN AND PROCESS CONTROL

This course begins with a strategy for experimentation of systems and processes. The strategy involves with deliberately changing the input variables to the system and observe the changes in the output of the system. Models are then created based on the inputs and outputs and the models are used to improve/optimize the system. This course provides a systematic approach of designing such experiments and analyzing the data with statistical models. These experimental design and analysis methods are widely used in multiple fields such as manufacturing, drug testing, website optimization, marketing, etc. After the system/process is optimized, then statistical process control can be used to monitor/improve the process on an ongoing basis. This course provides a powerful collection of Statistical Process Control tools that are useful in achieving process stability and improving capability through variability reduction. This is a project-based course with assignments from multiple industries and R is used for design, analysis, and control. Final project is a ‘hands-on’ experiment that is based on a simulated environment.

Prerequisite: PREDICT 410-DL Regression and Multivariate Analysis