University of Twente Student Theses
A hybrid recommender-system for startup scouting
Bosch, K.T.D. (2022) A hybrid recommender-system for startup scouting.
|
PDF
6MB |
| Abstract: | This design science research study investigates whether problems in the startup scouting process of Unknown Group can be solved by implementing a hybrid recommender-system, hereby improving efficiency and reliability of this scouting process. With use of a literature study, a design theory for a hybrid recommender-system for startup scouting was established. This design theory was translated to requirements that were supplemented by the direct stakeholders. These requirements were converted into design suggestions, which were assembled into an application architecture for the development of a prototype. The success for this solution to the problem was tested using the mean Average Precision and the Matthews-Correlation Coefficient as well as the inclusion of the requirements. Though the synthetic data testing seemed very promising, the recommender-system failed to provide a sufficient recommendation with real data. This confirmed the hypothesis that the data was too inconsistent and incomplete for proper data driven decision making, a major issue that should be a the top of the agenda for Unknown Group. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Business Information Technology MSc (60025) |
| Link to this item: | https://purl.utwente.nl/essays/90579 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page