Content

Skill booster: sustained and fun development of students’ future skills - Civic Innovation Platform

Skill booster: sustained and fun development of students’ future skills

The app idea of the start-up DayOff GbR and the Key Skills Centre (ZfS) at Kiel University is for students of all disciplines to receive support in developing future skills. Because along with subject-specific expertise, it is primarily skills such as self-management, collaborative and agile working, and problem solving which are crucial in an ever-changing working world. With the help of machine learning, students are presented with personalized, daily learning challenges based on both their personality and existing skills.

Why are you a strong team?

We have the common goal of creating a digital solution that will support many students in the development of their future skills. Daniela and Wibke from the Key Skills Centre have many years of experience in helping students to improve their skills and are familiar with the practical requirements. Lino and Corin from DayOff are experts in the playful design of micro-learning units and also know how to implement the skill booster technically.

Explain your idea in three sentences.

We aim to provide students with customised support in the development of their future skills wherever they need it. Through machine learning, learning content is selected to match the personality and existing skills of each individual user. As a result, students receive two to five minutes of customised learning tasks every day.

What makes your idea special?

We unite skills analysis, suitable learning content through machine learning, gamification and psychological findings for sustainable learning in one single application. We believe that learning content should not only be taught theoretically, but also actually applied in the everyday lives of students.

What are the next steps?

We want to develop a self-learning system that sets students daily (learning) challenges. For this, we will start by developing a skills model for the elaboration of a skills analysis in the next step. At the same time, we translate future skills learning content into these small (learning) challenges. After initial tests and user interviews, we then want to develop a machine learning algorithm that sends suitable daily (learning) challenges based on the skills analysis and interests.

Contact