The programme combines courses from different disciplines into one coherent master’s specialisation that is focused on business applications. As no advanced prior knowledge is required, core courses in computer and data science lay the groundwork for the more advanced seminars. The latter explore state of the art machine learning methods and apply them to real-life business problems.
This master’s specialisation consists of core courses, seminars, electives and a master's thesis distributed over 5 blocks of 8 weeks. In the first block, 3 core courses of 4 credits will each introduce you to the broad range of both knowledge and skills that you will acquire and perfect in the Master Data Science and Marketing Analytics.
Interactive seminars are a very important component of our programme. You will be involved full time in a seminar for an entire block, allowing you to dive deep into the material, guided by the lecturers. For these intensive courses, active participation and strong commitment is a must. The second and third block follow this format, starting with a focus on learning new methods, followed by a seminar where you will work on real-life business problems, putting the methods and skills obtained in earlier blocks to the test.
In the fourth block you will follow one final course and choose one elective.
You should already start thinking about your master’s thesis in January, but block 4 and 5 will be dedicated entirely to this task, which is based on research you have conducted yourself under supervision by a member of our academic staff. Erasmus Research & Business Support (ERBS) offers job market preparation sessions in block 5.
The curriculum consists of:
- 50 % computer science/machine learning
- 50 % marketing business
The key strength of machine learning techniques is their predictive ability. For marketing analysts this opens up many opportunities to improve customer experience, making shopping both more pleasant and effective, for example by providing accurate recommendations. Interesting business cases that will be covered include the composition of a set of relevant products, but also the identification of the customer’s stage in the buying process, allowing firms to provide the information that is most valuable at that stage to the customer.
Disclaimer: The overview below shows the programme curriculum for the academic year 2019/2020.
The Take-Off is the introduction event for all new students of Erasmus School of Economics. This year, the Take-Off will take place on Tuesday 5 September 2017. During this interesting introduction event, you will be provided with useful practical information and receive an introduction to your studies, meet your fellow students and our School.
Data science provides a new paradigm for the analysis of data. In this course, an introductory overview is given of data science. The main goal is to introduce several data science techniques. Amongst the techniques discussed are (penalized) regression including ridge, lasso, and elastic net regression, principal components analysis, and (multiple) correspondence analysis. The techniques are categorized in supervised and unsupervised learning methods. Special attention is given to the bias-variance trade-off and penalty approaches that reduce the variance in prediction at the cost of some bias. The practical implication is to use cross validation to to select optimal parameters with respect to predictive performance. The differences between statistical and computational approaches such as bootstrap and permutation testing for hypothesis testing are also discussed. Students apply the methods using the statistical language R in several group assignments.
In this course, students will have insights on:
- Introduction to marketing models
- Customer value models
- Segmentation and targeting analysis
- Techniques to position products
- New product diffusion
- Conjoint analysis
- Pricing and promotion decisions
- Analytics for digital marketing
This course provides an introduction to programming in R.
- Introduction to R, data structures and functions
- Graphical visualizations in R
- Data manipulations in R
- R Markdown
- Relating R to databases
- Programming in R, through loops, control flow and writing of functions
- Programming with functions
After a general introduction, several data science/machine learning methods are treated sequentially. First, the basics behind a technique are introduced after which the students deepen their knowledge and understanding of the methods by using selected research papers and by implementing and applying the methods to real data.
The seminar is taught in a workshop format with a strong emphasis on student participation and interaction. Class size is limited to a maximum of 24 students. We discuss and analyze recent research papers to provide a "state-of-the-art" overview of the methods used in this area. Students are asked to critically assess, present and discuss the research papers. Reviewing state-of-the art methods and their application in business settings will help students to assess whether (and how) data can be used to help answer real world business problems.
The students are divided in small groups to provide a solution to a real world management problem. Usually these management problems are put forward by a company that will be involved with the course. First, the relevant literature on the management problem is studied. Integrating the literature with the management problem, a formal research question is developed. In the next step, the required/available data in combination with an appropriate analysis technique is determined in order to best answer the research question. Models will then be estimated based on the available (company) data. Model outcomes will then be interpreted in order to answer the research question. The final step is then to translate this answer to a solution to the management problem. Reporting on this whole process will be done in the form of a research report, an executive summary and a management presentation. Each group of students will also receive and be asked to provide feedback on the approach taken and solution that is provided.
Block 4 (1 obligatory course + choose 1 elective)
In an age where customer opinion and feedback can have an immediate, major effect upon the success of a business or organization, marketers must have the ability to analyze unstructured data in everything from social media and internet reviews to customer surveys or phone logs. This course provides students with tools that enable them to effectively implement and use text analytics in a marketing context. In the course the complete analysis process, from data input, summary and statistical analysis, will be covered.
Next to the weekly lectures, students will make a group assignment to gain hands on experience with the techniques from the course.
You could also choose another Economics and Business master's course as your elective.
While you have to start thinking about your thesis already in spring, the last two blocks of the programme are especially devoted to the Master’s thesis. The thesis is written individually under close supervision by one of our academic staff members.