Web Platform for the Innovation Ecosystem of ImpactLab FHNW
The new web platform of ImpactLab allows FHNW students or staff to store their business ideas and required competencies, whereas experts from the university or private sector can offer their expertise. By offering mentorships, the path from idea to implementation by founding a startup is shortened.
Jan Wächter, 2022
Bachelor Thesis, Hochschule für Wirtschaft FHNW
Betreuende Dozierende: Emanuele Laurenzi
Keywords: Innovation matchmaking entrepreneur startup incubator mentor
ImpactLab FHNW is the incubator that helps students in creating startups. Currently, the innovation ecosystem is growing with several stakeholders such as: - students with business ideas - students willing to support other students having business ideas - alumni, researchers, professors, and external experts that act as mentors - companies that financially support events. Keeping everything in an Excel sheet is not sustainable. Moreover, if a student has a business idea, he/she should be matched with a mentor, which is currently done manually and is time-consuming.
The intention is to build up a web platform in order to perform automated matchmaking between future FHNW entrepreneurs and mentors. A literature review on the topic of knowledge graph, API integration, matchmaking algorithm and natural language processing is conducted. Additionally, the relevant software components are evaluated which are required to answer the research questions.
As a result, ImpactLab FHNW has a new web platform to host potential mentorships through matching FHNW students or staff with mentors. To achieve this, a graph database in combination with RDF4J, Spring Boot and WordPress as Frontend is used. The matchmaking happens around competencies, a property collected both from the FHNW entrepreneurs as well as the experts. If one offers and one needs the same competency, a mentorship is proposed. This is achieved by having a mixed ontology between Schema.org and ImpactLab's own. Natural language processing can contribute by using word embedding to classify the similarity of competencies and recommend matchmaking after a certain value. However, this has only been explored theoretically.
Studiengang: Business Information Technology (Bachelor)
Fachbereich der Arbeit: