As a student in the Business Analytics and Quantitative Marketing master you learn how to make use of the enormous amount of data that is available in corporations and other organisations to support decision-making in business. You will be introduced to the latest research techniques and will, after completion of the programme, have the technical skills to keep up with and contribute to future developments in this field.
The programme is made up of 7 core courses (each 4 ECTS), a seminar (12 ECTS) and the master's thesis (20 ECTS, including the master's thesis proposal). Each core course focuses on a particular set of techniques or a methodology. In the seminar, students form small groups and focus their complete attention to solve an actual business case. The seminar is organised in cooperation with a number of companies.
Curriculum
The curriculum consists of:
- 20% Statistics
- 30% Econometrics
- 20% Machine learning & Computer Science
- 30% Seminar
As the curriculum shows, this programme has a technical focus. You will study the mathematical and statistical details of modern methods with applications in marketing and business in the broad sense.
In class
In the seminar students study real-world problems that are put forward by participating companies. Some examples of problems that were tackled in the seminar in the past:
- How to predict which TV show an individual will watch and for how long?
- How to detect whether a respondent really pays attention when filling out a survey?
- How can so-called graphical models be used to summarise data sets with many variables?
- How can we use the text of conversations to understand the areas in which a chatbot can be improved?
- What impact does price have on online shopping?
For all these questions students developed appropriate models and methods, implemented these in software, and provided practical advice to the involved company.
Study schedule
The Take-Off is the introduction programme for all new students at Erasmus School of Economics. During the Take-Off you will meet your fellow students, get acquainted with our study associations and learn all the ins and outs of your new study programme, supporting information systems and life on campus and in the city.
This course deals with several (teoretical and applied) advanced topics in Microecometrics such as:
- methods of moments, general methods of moments;
- linear, dynamic, and nonlinear panel data models;
- heterogeneity and cross-section dependence in panel data;
- duration models;
- treatment effect evaluation.
Bayesian Econometrics plays an important role in quantitative economics, marketing research and finance. This course discusses the basic tools which are needed to perform Bayesian analyses. It starts with a discussion on the difference between Bayesian and frequentist statistical approach. Next, Bayesian parameter inference, forecasting and Bayesian testing is considered, where we deal with univariate models, multivariate models and panel data models (Hierarchical Bayes techniques). To perform a Bayesian analysis, knowledge of advanced simulation methods is necessary. Part of the course is devoted to Markov Chain Monte Carlo sampling methods including Gibbs sampling, data augmentation and Monte Carlo integration. The topics are illustrated using simple computer examples which are demonstrated during the lectures.
- Introduction
- Regularization
- Trees, Forests and Ensemble Methods
- Support Vector Machines
- Clustering
- Neural Networks (Deep Learning)
- Reinforcement Learning
This content will be complemented with several assignments and readings.
Companies currently have many sources of data available. In this course, we focus on multivariate relations in the data. This course deals with various multivariate statistical techniques to analyze such data sets. Examples are:
- Discriminant analysis/Classification
- Canonical correlation analysis
- Factor analysis
The course also contains the introduction to robust statistics and its interplay with the multivariate statistical methods.
In each week a different modeling technique is discussed. Examples are models for sales, models for market shares, Hidden Markov Models, Conjoint analysis, modeling heterogeneity, and modeling dynamics. For all topics we will discuss the technical details of the techniques as well as how to apply the techniques and how to interpret the model results.
The course starts by introducing various Computer Science topics relevant for Business Analytics. After that, in order to be able to query relational databases, the SQL query language will be studied. As means to process Big Data we will look at parallel computing models, focusing on the Map-Reduce parallel computing style.
Also, with the purpose of reducing the number of computations for finding similar items (a fundamental data mining problem), we will describe Locality-Sensitive Hashing.
In order to better assimilate the topics covered during lectures, the students will work in teams on several assignments on the discussed topics. The students will also write a report describing the proposed solutions. In addition a larger individual assignment that involves programming will result in a short paper.
In this course we will focus on nonparametric statistics and kernel methods.
We are familiar with methods such as maximum likelihood or linear regression. These are called parametric analysis as the data are assumed to come from a certain distribution (e.g., normal distribution) or have a certain relationship (e.g., linear relationship). Nonparametric analysis intends to uncover patterns in data without such assumptions. These methods are much more flexible and robust, but also come at a different cost.
Kernel is an essential concept in nonparametric statistics and helps facilitate many nonparametric methods. It also has many applications in machine learning and allows to extend many basic methods into more flexible versions, such as kernel PCA and kernel SVM.
Other possible topics for this class include a review of cross validation, bootstrapping, reproducing kernel Hilbert space and semiparametric statistics, depending on the level of the class. (To be decided later by the instructor)
The assessment will be based on the combination of two types of assignments. There will be a mathematical written assignment every week following the lecture, and there will be 3-4 practical assignments where you need to programme and apply the methods on data.
The students are divided in small groups. Each group works on a research question. Usually this research question is put forward by a company. First, the relevant literature is studied. Next, the research question is translated in one or more models. To estimate the parameters of the models, (company) data is used. Much attention will be paid to the selection of the best possible model, given the research question. This model can be any model dealt with in the various courses, but it can also be a model that needs to be developed by the students themselves. The model parameters are estimated, and the model results are interpreted within the light of the research question. The final results will be presented in a scientific report and a presentation.
Proposal for the Master thesis Econometrics and Management Science. This proposal can be used as a part of the Master thesis. There is no grade for this proposal.
The thesis is an individual assignment about a subject from your Master's specialisation. More information about thesis subjects, thesis supervisors and the writing process can be found on the Master thesis website.
Disclaimer
The overview above provides an impression of the curriculum for this programme for the academic year 2023-2024. It is not an up-to-date study schedule for current students. They can find their full study schedules on MyEUR. Please note that minor changes to this schedule are possible in future academic years.