- Broadening minor
- Minor code
- 10 weeks
Every day, millions of consumers voice their opinions in product-review websites, blogs and chat rooms. They spontaneously produce massive amounts of user-generated content (UGC), most of which is textual and freely available for analysis. At the same time, online and offline retailers collect rich data sets that contain valuable information about the purchases of individual customers. In this era of big data, the availability of novel, larger and more diversified data sets opens up exciting opportunities for marketing researchers and practitioners.
However, the characteristics of big data (volume, velocity, variety) also pose challenges for modelers. With so much data available, it can be hard to determine what information is correct or how to separate signal from noise. For example, how can you extract information about market structure and consumer preferences from purchase data? To make this more difficult, UGC data is often unstructured and textual. Do you know how to analyze this data? And how do you go from insights to marketing decisions?
All that is needed to address these challenges is the right set of tools and the training that helps you to use the tools correctly. This course first teaches how to formalize marketing problems as statistical models. It then shows how to solve marketing problems by complementing classical econometric techniques with modern machine learning (ML) methods. You will find tools and conceptual frameworks needed to identify and exploit the opportunities that big data sources open up.
The course has three modules, each containing lectures and hands-on activities:
- “Mine your Own Business in Blogs, Reviews and Tweets”
- “Purchase Prediction with Boosted Trees”
- “Neural Networks–From Market Structure Analysis to Prescriptive Marketing”
The objectives of this course are to equip you with the tools and methods necessary to:
- Obtain insights on consumer preferences and behavior from user-generated data.
- Understand the potential of user-generated content (UGC) as a way to listen to the voice-of-the-consumer, expressed in unstructured data such as texts in blogs and product reviews.
- Formalize marketing decisions as supervised or unsupervised machine learning problems.
- Analyze real-world loyalty card data to solve prescriptive marketing problems.
- Learn the necessary tools to efficiently implement machine learning models and pipelines.
- Learn how to work in groups on ML and data science projects.
This course relies a lot on statistical concepts and tools you are expected to apply independently (or study independently to catch up with eventual gaps in your statistical knowledge). Successful participation in at least one advanced statistics or data science courses is strongly recommended, for example, Applied statistics (FEB11005), Econometrics 1 (FEB22004X), Introduction to Multivariate Statistics (FEB22003X), Seminar in Econometrics (FEB23012 or FEB23016), or Statistics (FEB21007X or BT1111 or BT1211). Please note that other ML, data science, statistics, and programming courses might cover more specific knowledge that can be useful for this course.
In addition, you must be proficient in Python (this course does not teach Python) and have a good understanding of statistics and linear algebra. A basic knowledge of computer science and writing software is helpful.
All RSM minors have mandatory attendance.
Overview content per week:
The course has three modules, each containing lectures and hands-on activities.
In the first module (“Mine your Own Business in Blogs, Reviews and Tweets”) we will work with various types of UGC, with a strong emphasis on textual data. We will discuss and use tools to help you automate the detection of both content and sentiment from texts produced by consumers.
The second module (“Purchase Prediction with Boosted Trees”) focuses on the application of supervised ML methods to predictive and prescriptive marketing problems. The module also introduces important theoretical and practical principles for designing and implementing ML pipelines.
In the third module (“Neural Networks–From Market Structure Analysis to Prescriptive Marketing”), we will use representation learning and deep learning techniques to model market structures in retailing applications and leverage insights for prescriptive marketing applications.
There is one major “module assignment” to be handed in at the end of each module. In the assignments you will apply the methods, templates, and scripts seen during the lectures.
- Group Assignments: These are done in groups of 3 to 4 students but the individual grade will vary across students within a group to reflect dedication and contribution. These weights are based on peer assessment and the professor assessment of the actual individual contribution in the overall group output.
- Individual Assignments
Details will be announced at the start of the course.
Method of examination
- Participation (4%)
- Group Assignments (32%): these are done in groups of 3 to 4 students
- Individual Assignments (64%)
The resit will be a written test that will test in detail your ability During the test, students will be asked to demonstrate that they have the knowledge and skills needed to complete the report that is to be replaced. For example, the student may be given data and asked to calculate intermediate steps, or to describe specific calculations that were involved in that report.
Composition final grade
- Participation (4%)
- Group Assignments (32%)
- Individual Assignments (64%)
- Detailed individual feedback via email
- Additional individual feedback available in person during office hours booked in advance
Frequently Asked Questions
- Email address
Please read the application procedure for more information.