- Data Analytics and Modeling (m)
- Management Analytics (c)
- Process and Supply Chain Management (c)
Students who are interested in acquiring hands-on skills in data structuring and predictive modeling to support business decision-making. There are no formal prerequisites for the course beyond first-year courses.
In person – Weekly sessions consisting of lectures, guest speakers, and student presentations
- Expose students to key Predictive Analytics and Machine Learning tools
- Enable students to:
- Structure business decisions as “analytical” problems
- Identify which data sources are needed to provide an answer
- Structure the data for analysis using common data management operations (joins, aggregations, disaggregations, etc.)
- Understand and apply appropriate analytical tools
- Derive managerial insights from the analytical results
- Communicate the findings effectively
- Expose students to some effective applications of predictive modeling across a variety of functional areas and make them aware of both promises and challenges involved.
The course is designed for students interested in advanced analytics and data-driven decision-making techniques. Analytics (data science/ data mining/ machine learning) skills are increasingly important across a wide spectrum of industries and functional areas. In this hands-on course students will be exposed to all aspects of predictive analytics, starting with data acquisition, preparation and structuring, proceeding to data modeling techniques, and then using the results to support effective decision-making. The course will expose student to advanced software tools for data management and manipulation, data visualization and modeling.
The course will be divided into several modules focusing on the main steps in a typical Predictive Analytics project:
- Translation of a business problem to a set of ‘analytical” questions. This involves identifying the key elements of the analytical study to be conducted (unit of the analysis, data to be measured, evaluation of results, implementation issues)
- Acquisition, cleaning and transformation of data using SQL-type tools
- Conducting preliminary exploratory analysis using descriptive tools, as well as data visualization and dimensionality reduction techniques
- Identifying and applying appropriate analytical models. We will use a variety of tools, ranging from multiple and logistic regression to decision trees, random forests, boosting and regularization methods, clustering, neural networks, and other tools.
- Effective communication of analytical findings to business managers.
The class builds on skills acquired in first-year courses on Statistics, Data and Models. It is one of the core courses for the Management Analytics major. While this course is an excellent complement to RSM2408 Modeling and Optimization for Decision Making (another core course), the latter is not a pre-requisite – all analytical techniques employed will be introduced within the course. We will discuss applications of analytical techniques to business issues drawn from many functional areas, including marketing, operations, strategy, etc.
Evaluation and Grade Distribution
|Group Case Analyses||3 submissions*||40%|
|Individual Case Analyses||3 submissions||40%|
*Please note that the list below may be adjusted as new software tools become available*
SAS JMP Pro software (available for free; please download from the Rotman Hub)
Note: we may also introduce R or Python as an alternative for students interested in learning these tools
Textbook: “Data Mining for Business Analytics; Concepts, Techniques and Applications with JMP Pro”, by G. Shmueli, P. Bruce, M. Stephens, N. Patel
- SAS JMP Pro software (available for free; please download from the Rotman Hub)
- Note: we may also introduce R or Python as an alternative for students interested in learning these tools
- Textbook: “Data Mining for Business Analytics; Concepts, Techniques and Applications with JMP Pro”, by G. Shmueli, P. Bruce, M. Stephens, N. Patel
- Note: there are versions of this textbook available using R and Python instead of JMP Pro.
- Course package, lecture notes, selected readings