Teacher(s)
Language
English
Prerequisites
1 basic marketing course
Main themes
Humanity has generated and stored more data in the last 24 months than in the millions of years before that. World's data production, analysis, and consumption are growing exponentially and this trend is not slowing down anytime soon.
In such environment understanding and working with data has become crucial for companies to survive, innovate and grow. For this reason, companies are more and more demanding of data literate workforce - and marketing is no exception.
The fundamental pillars of marketing' acquire and retain customers - will not change, but the means available to marketers to achieve their objectives are changing fundamentally. This course will introduce one of the most promising new mean available to marketers to achieve their objectives: Big Data analysis.
Themes that will be addressed are:
Big data, Data mining, Artificial Intelligence
In such environment understanding and working with data has become crucial for companies to survive, innovate and grow. For this reason, companies are more and more demanding of data literate workforce - and marketing is no exception.
The fundamental pillars of marketing' acquire and retain customers - will not change, but the means available to marketers to achieve their objectives are changing fundamentally. This course will introduce one of the most promising new mean available to marketers to achieve their objectives: Big Data analysis.
Themes that will be addressed are:
Big data, Data mining, Artificial Intelligence
Learning outcomes
At the end of this learning unit, the student is able to : | |
| 1 | On successful completion of this program, each student will acquire the following skills :
|
Content
The content of the lectures will be divided into 3 Chapters:
- Introduce the notion of big data and data management (data storage, relational databases, noSQL, AI)
- Data Mining (supervised and unsupervised learning, predictive analysis, dimension reduction)
- Text and image mining (topic modeling, text classification, keyword extraction, trend analysis, image analysis)
Teaching methods
This course will cover the theory of some popular methods in data mining and machine learning with practical applications in marketing. No programming skills are needed. The idea of the teaching is that the instructor will present the theory behind the methods and illustrate how these methods are applied in marketing.
For theoretical classes, the slides used are made available in Moodle. More specific references are provided during the lectures or in the slides.
As several practical cases are presented in the theoretical lectures, all the the data source and workflows will be made available on Moodle so that students can reproduce the results.
For theoretical classes, the slides used are made available in Moodle. More specific references are provided during the lectures or in the slides.
As several practical cases are presented in the theoretical lectures, all the the data source and workflows will be made available on Moodle so that students can reproduce the results.
Evaluation methods
The evaluation consistes of two parts
1. A written exam (closed book) that weights for 60% of the total. This exam will cover all the material seen in class (both theoretical and more applied).
2. A team project on some specific marketing questions chosen by the students that weights for 40% of the total. The software used for this course is a "no code" open source software called orange (https://orangedatamining.com/). No programming skills are a priori needed but students that would like to input some additional python code can do it using some specific python widgets (this is however generally not needed).
Several tutorial for using efficiently orange are available on orange's youtube channel (https://www.youtube.com/@OrangeDataMining)
Only the written exam (part 1) can be retaken in the second session in case of failure. The grade for part 2 (the team project) will be automatically carried over to the second session.
1. A written exam (closed book) that weights for 60% of the total. This exam will cover all the material seen in class (both theoretical and more applied).
2. A team project on some specific marketing questions chosen by the students that weights for 40% of the total. The software used for this course is a "no code" open source software called orange (https://orangedatamining.com/). No programming skills are a priori needed but students that would like to input some additional python code can do it using some specific python widgets (this is however generally not needed).
Several tutorial for using efficiently orange are available on orange's youtube channel (https://www.youtube.com/@OrangeDataMining)
Only the written exam (part 1) can be retaken in the second session in case of failure. The grade for part 2 (the team project) will be automatically carried over to the second session.
Other information
Students are expected to have a good understanding of statistics and mathematics (BA level).
No programming skills are needed as a "no code" solution has been adopted for the practical work (https://orangedatamining.com/)
The team project will be evaluated on the basis of a written document and, possibly, an oral presentation, the details of which will be explained during the course. The datasets used and the workflow implemented have to be described in the document and made available (probably via Moodle) for the evaluation. Potential sources for data will be discussed in class.
In this course, we promote the responsible and critical use of generative AI. If these tools are used, it is crucial to explicitly indicate their application and properly acknowledge all relevant sources.
No programming skills are needed as a "no code" solution has been adopted for the practical work (https://orangedatamining.com/)
The team project will be evaluated on the basis of a written document and, possibly, an oral presentation, the details of which will be explained during the course. The datasets used and the workflow implemented have to be described in the document and made available (probably via Moodle) for the evaluation. Potential sources for data will be discussed in class.
In this course, we promote the responsible and critical use of generative AI. If these tools are used, it is crucial to explicitly indicate their application and properly acknowledge all relevant sources.
Online resources
All the slides presented in class as well as the workflows and data source will be made available via Moodle.
Some specific additionnal references that could beinteresting for students will be provided in class or in the slides.
Some specific additionnal references that could beinteresting for students will be provided in class or in the slides.
Bibliography
Slides are provided through Moodle.
No compulsory reading is needed for this course other than the slides. However some specific references are provided in class for those interested.
Many datasets used in class come from https://www.kaggle.com/
The (free) software used can be downloaded at: https://orangedatamining.com/.
Many explanations for the methods used are available in orange's youtube channel (https://www.youtube.com/@OrangeDataMining)
Faculty or entity
