Project Abstract

This project addresses critical challenges in the online gig economy by proposing an advanced recommendation algorithm to match freelancers with suitable clients and relevant training modules. With the ever-growing demand for freelancers and the increasing complexity of project requirements, accurate matching is crucial for both clients and freelancers to thrive. By focusing on the development of an adaptive learning algorithm, the project aims to provide accurate project recommendations, and to ensure long-term relevance by being able to adapt to new types of skills and projects being introduced to the system. Through extensive research on recommender systems and a structured software development methodology, this project has produced a robust recommendation system that enhances the efficiency and accuracy of matching freelancers with clients and training opportunities. The main findings show the significance of tailored recommendations in improving collaboration success and increasing client satisfaction, while also facilitating continuous career growth for freelancers. The recommendation algorithm is implemented using Python and can be interacted with using a frontend webpage. DBngin has been used to host a local database server, and the Flask framework has been used to provide a compatible web server for Python to be accessed by the webpage. The main findings of this project highlight the effectiveness of the developed recommendation algorithm in producing accurate recommendations for projects and training modules. It shows the importance of precise recommendations that consider a variety of criteria. Overall, this project highlights our understanding of optimising the gig economy through tailored recommendation algorithms and demonstrates why they are needed to contribute to success of clients and freelancers. Additionally, the work highlights the importance of these algorithms for ensuring long-term relevance and competitiveness of freelance platforms.

Keywords: Algorithms, Recommender Systems,

 Conference Details

Session: Poster Session A at Poster Stand 137

Location: Sir Stanley Clarke Auditorium at Tuesday 7th 13:30 – 17:00

Markers: Arnold Beckmann, Julian Hough

Course: BSc Computer Science, 3rd Year

Future Plans: I’m looking for work