PROJECT IDEA RECOMMENDER

Author

Nidish Kumar S, Kaviyarasan S, Ragul S, Ms. Vijayalakshmi S

Abstract

 Choosing a suitable software project is a difficult early decision for students of computing programmes, yet most students must make it without a reliable way to judge whether an idea fits their programming skills, team size and available time. Project ideas are scattered across many sources, are described in different ways, and are rarely tailored to the person reading them, so unsuitable topics are often discovered only after weeks of effort. This paper presents the Project Idea Recommender, a web-based application that accepts a student’s preferences, compares them with a structured catalogue of project records, and presents a ranked list of suitable projects through a single interface. The system combines user authentication, preference capture, weighted multi-factor matching, threshold-based filtering, factor-by-factor score explanation, side-by-side comparison, skill gap analysis, automatic weekly roadmap generation and recommendation history storage. The application is implemented with a React and TypeScript frontend built with Vite, Firebase Authentication, Cloud Firestore and Firebase Hosting. Each project receives a score out of one hundred from seven weighted factors, and only projects scoring above a threshold are shown. The catalogue in the current implementation holds 305 projects in 20 domains. The scoring is rule-based and transparent, and it does not use machine learning. Automated checks of the code and the data have been run, while the functional and usability evaluation with students remains to be completed.

Keywords

Project Recommendation, Recommender Systems, Weighted Matching, Skill Gap Analysis, Explainable Scoring, Personalised Learning, React, Firebase.

Full Text:

Download Paper PDF

References

1.F. Ricci, L. Rokach, and B. Shapira, Eds., Recommender Systems Handbook, 3rd ed. New York,NY, USA: Springer, 2022.
2.G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,” IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 6, pp. 734–749, 2005.
3.R. Burke, “Hybrid recommender systems: Survey and experiments,” User-Modeling and User-Adapted Interaction, vol. 12, no. 4, pp. 331–370, 2002.
4.P. Lops, M. de Gemmis, and G. Semeraro, “Content-based recommender systems: State of the artand trends,” in Recommender Systems Handbook, F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds. Boston, MA, USA: Springer, 2011, pp. 73–105.
5.N. Tintarev and J. Masthoff, “A survey of explanations in recommender systems,” in Proc. IEEE23rd Int. Conf. Data Engineering Workshops, 2007, pp. 801–810.
6.J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl, “Evaluating collaborative filtering recommender systems,” ACM Transactions on Information Systems, vol. 22, no. 1, pp. 5–53, 2004.
7.J. Nielsen, Usability Engineering. San Diego, CA, USA: Academic Press, 1993.
8.React. React Documentation. Available at: https://react.dev/
9.Google Firebase. Firebase Documentation. Available at: https://firebase.google.com/docs
10.Vite. Vite Documentation. Available at: https://vite.dev/guide/
11.OWASP Foundation. OWASP Application Security Guidance. Available at: https://owasp.org/

Share your valuable work from Social Media Buttons