REPUTATION AND TRUST MANAGEMENT SYSTEM FOR GIG PLATFORMS
Abstract
ABSTRACT
The gig economy relies heavily on reputation systems to foster trust between workers and clients, yet existing systems suffer from biases, lack of transparency, and non-portable reputations, as highlighted by Chen (2025). This study presents the design, implementation, and evaluation of a Reputation and Trust Management System (RTMS) for gig platforms, addressing these challenges through machine learning, explainable AI, and blockchain-inspired technologies. Using the Fiverr Data Gigs dataset (12,348 records), the RTMS was developed with a Flask-based web application, a RandomForestClassifier for bias detection, an SQLite database, and a tamper-proof ledger. The system achieved 92% accuracy in detecting biased reviews, processed 150 review submissions with a 0.75-second average response time, and provided transparent explanations via SHAP, with 60% of bias predictions attributed to ratings. The blockchain-inspired ledger ensured 100% integrity for reputation portability. Tested locally with Docker support for scalability, the RTMS offers a fair, transparent, and portable solution for gig economies, with implications for workers, clients, and platform developers. Future work includes integrating real blockchain networks and real demographic data to enhance applicability.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.