Student Projects

We are offering a range of Master Projects and Semester Projects in data mining and machine learning for (vocational) education ecosystems.

To apply, you are requested to send an e-mail to the contact person, mentioning the topic of interest and attaching your grade transcripts. If you would like to receive more information on our research, do not hesitate to contact us!

Please, note that the list of topics below is not exclusive. In case you have other ideas or proposals, you are welcome to contact a senior member of the lab and talk about possibilities for a tailor-made topic.


Master Thesis in Collaboration with the Startup Classtime

Classtime (​www.classtime.com​) is a web-based engagement and examination platform for modern teaching. It enables a more intensive interaction between teachers and learners, increases the transparency of the learning progress, and helps teachers save time – be it in face-to-face or online distance learning. The functionalities of the platform include formative and summative assessments, with an automatic correction of homeworks, exams, and checks of prior knowledge. It also provides the possibility to implement modern pedagogical approaches, such as flipped classroom and gamification. The startup has around 15 team members and is based in Zurich and the USA.

The goal of this master project is to implement a recommender system ​to support teachers in the design of assessment questions. The objective is to ​further advance the existing question creator ​functionality, in such a way that it provides teachers with automatically generated suggestions to enhance their assessment questions with pedagogically meaningful ​information/hints. To this end, the student involved in this master project will leverage real datasets from the platform to implement the recommender system. Finally, the student will be involved in the planning and execution of ​user studies ​to evaluate the effectiveness​ of the recommender system.

This is a ​paid master project co-supervised by the D-VET Laboratory and Classtime. It is supported by the NestED project of the Swiss EdTech Collider, which provides the financial funding for the student’s salary.

Keywords:​ Recommender systems, learning assessment, assessment questions.

Preferred skills:​ Experience with machine learning algorithms; interest in pedagogy; proficiency in Python; proficiency in English; proficiency in React / Redux would be a plus.

Useful tools:​ Jupyter Notebooks, NLTK, Scikit-Learn, Tensorflow.

Contact:​ Dr. Christian Giang (E-mail: [email protected])


Intelligent Systems for Adaptive Teaching Interventions in Flipped Classrooms

Nowadays, flipped classrooms are receiving an increasing interest in the instructional design field. This learning strategy requires students to follow pre-class learning activities, before meeting with the teacher and the other peers for an in-person discussion and assessment. For pre-class activities, teachers often provide students with videos and digital content by means of an online learning platform. Engaging with pre-class activities is essential for the success of flipped classrooms, as these activities prepare students for a more active participation in face-to-face lessons.

Current projects in this field focus on analyzing students’ behavior during online pre-class activities, in order to enable effective content personalization and adaptive teaching assistance. For instance, we are designing and implementing intelligent early warning systems that, by anticipating whether a student will pass or not the final exam, serve as a means for timely interventions. Other examples of systems we are interested in include response correctness prediction systems, which predict the probability a student correctly answers an exam question. The latter systems would enable personalized learning activities and suggestions for topics requiring revision. Besides optimizing these systems for accuracy, we are detecting instances of algorithmic unfairness and designing countermeasures that ensure fair treatments across subgroups of students, while retaining the model accuracy. Furthermore, given that there is often no understanding on how the model came to a given prediction, we are investigating strategies for making predictions explainable and transparent, allowing teachers and students to better react to model’s decisions.

Keywords: Machine Learning, Clickstream Analysis, Early Warning Systems, Response Correctness Prediction, Algorithmic Fairness, Explainability.

Preferred Skills: Proficiency in Python; Experience with Machine Learning Algorithms.

Useful Tools: Jupyter Notebooks, Numpy, Pandas, ScikitLearn, Seaborn, TensorFlow.

Contact: Dr. Mirko Marras (Website: mirkomarras.com, E-mail: [email protected])


Empowering Massive Open Online Course Platforms with Machine Learning Models


Image courtesy of EPFL Courseware.

Over the last years, Massive Open Online Course (MOOC) platforms have been providing life-changing educational opportunities to millions of individuals, with unrestricted participation to any course of their choice, anytime, anywhere. Notable examples include Udemy, Coursera, edX, and Udacity. Top tier universities, such as EPFL, are now offering a wide range of MOOCs as well, providing students with a way to learn in a setting similar to an online class, but with a loosely structured schedule and the opportunity of interacting with a large number of peers from around the world. However, scaling up education online towards these numbers is presenting core challenges, such as hardly manageable classes and overwhelming content alternatives.

Thanks to the wide availability of learning data and increasingly higher performance computing, data mining and machine learning have the potential to turn the current challenges into an unparalleled opportunity. Our goal in this research area is to understand how individuals interact with online learning platforms and provide them with timely supporting services. Our projects range from personalized recommendations (e.g., courses you might be interested in or peers who may have similar interests) to dropout predictions aimed at anticipating whether and why a student will not complete a course, from sentiment analysis on students’ reviews to grasp course elements that need improvement to semi-automated grading systems that help teachers in dealing with a large number of assignments to be checked, and more. Moreover, as these technologies play a relevant role in the educational landscape, possibly affecting a huge number of individuals, we are also interested in analyzing them from a beyond-accuracy perspective, such as on how the considered systems deal with ethics, fairness, transparency, and accountability objectives.

Keywords: Neural Networks, Deep Learning, Clickstream Analysis, Dropout Prediction, Recommender Systems, Sentiment Analysis.

Preferred Skills: Proficiency in Python; Experience with Machine Learning Algorithms.

Useful Tools: Jupyter Notebooks, Scikit-Learn, Tensorflow, SpaCy, NLTK.

Contact: Dr. Mirko Marras (Website: mirkomarras.com, E-mail: [email protected])


Natural Language Processing for Learning and Performance Documentation Tools


Image courtesy of realto.ch.

In vocational education, learning and performance documentation (LPD) tools are often used to help apprentices self-reflect on their learning processes. Such tools can, for instance, serve as a journal in which apprentices write down their experiences made in companies and/or vocational schools. Moreover, the entries can be evaluated by their respective supervisors and/or teachers, in order to provide them with appropriate support and guidance. To gain more insight on the apprentices’ experiences, natural language processing (NLP) can be applied to their LPD entries. The results can be used to provide apprentices, supervisors and teachers with additional information about the learning process. Especially when applied to large LPD data sets collected over long periods, it can provide insights that otherwise would be challenging to determine.

The goal of this project is to apply NLP to a dataset collected from chef apprentices who used a web-based LPD to log their experiences and recipes. The data logs in this project are in French and Italian, hence interested students should be proficient in at least one of these languages. For more details on the project, please do not hesitate to contact us!

Keywords: Natural Language Processing, Learning and Performance Documentation, Learning Journals.

Preferred skills: Proficiency in Python; Experience with machine learning algorithms; Proficiency in French and/or Italian.

Useful tools: Jupyter Notebooks, NLKT, Scikit-Learn, Tensorflow.

Contact: Dr. Christian Giang (E-mail: [email protected])


Interactive Simulations and Learning Games for Vocational Education


Image courtesy of the University of Colorado Boulder.

Interactive simulations can often be a helpful learning tool, providing a safe environment in which learners can freely explore and experiment without the dangers, risks and constraints of real-world setups. When appropriately utilized by teachers and students, such tools can especially facilitate the understanding of concepts that are normally difficult to grasp. The instantaneous feedback provided, such as visualizations and animations, can support students’ comprehension by making mechanisms visible that otherwise would remain hidden. Another alternative having the goal to innovate traditional instructional approaches is represented by learning games (or serious games). Through gamification, these applications aim at conveying learning content in a more playful way, capitalizing on the idea that such approaches may have a positive impact on learning motivation and engagement.

The vocational training for many professions could benefit from the targeted use of interactive simulations and/or learning games. At this moment, the laboratory is interested in developing and analyzing user interactions with chemistry simulations for lab technicians, thermal simulations for heating technicians, simulations for electronics technicians using mobile robots, learning games for vocational education in the global south. For more details on the projects, please do not hesitate to contact us!

Keywords: Interactive Simulations, Learning Games, Gamification

Preferred skills: Experience with programming; Interest for digital games; Experience with web/app development can be helpful.

Useful tools: Unity, HTML5, Android Studio

Contact: Dr. Christian Giang (E-mail: [email protected])