University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Fraud Detection in Reward-Based Crowdfunding : A Framework for Identifying Fraudulent Campaigns
Knoop, L.S. (2025) Fraud Detection in Reward-Based Crowdfunding : A Framework for Identifying Fraudulent Campaigns.
|
PDF
479kB |
| Abstract: | Platforms for reward-based crowdfunding, such as Kickstarter, provide opportunities for innovation but also give a chance for possibly fraudulent behaviour. Through an analysis of two high-risk subcategories, tabletop games and high-tech gadgets, this study intends to identify characteristics that indicate campaign fraud. The independent variables, minimum reward, campaign duration, word count, spelling error percentage, and sentiment score, are investigated. We manually verified 348 campaigns to conduct an analysis to determine whether they could be fraudulent. These campaigns were selected on the criterion that they did not enter the public market. To determine whether a crowdfunding campaign is considered fraud, five criteria are created. When at least three out of five criteria are met, the campaign is considered to be fraudulent. This research contributes to theory in the crowdfunding field by addressing how fraud connects to observable campaign characteristics. Crowdfunding platforms, backers, and campaign creators can benefit from this model by identifying suspicious and fraudulent behaviour. Findings imply that the risk of a campaign being fraudulent is not random and can be predicted by using publicly available data. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 85 business administration, organizational science |
| Programme: | International Business Administration BSc (50952) |
| Link to this item: | https://purl.utwente.nl/essays/106769 |
| 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