Email: m.kamran@cuiatk.edu.pk
Degree | CGPA | Institute |
---|---|---|
MSc Software Engineering | 3.29 | University of Engineering and Technology Taxila, Pakistan |
BSc Software Engineering | 3.10 | University of Engineering and Technology Taxila, Pakistan |
FSc(Pre. Engineering) | 82.82% | Federal Board of Intermediate and Secondary Education Islamabad |
TV Done for you (https://tvdfy.com/)
TaxPedia (http://taxpedia.in/)
GM Insurance ( https://gminsuranceservices.com/)
MY Islam ( https://myislam.org/)
Zelsart ( https://www.zelsart.com/)
Healthy App (https://healthyappforyou.twizard.io/)
Insta Iron (https://www.instairon.com/)
ZoxTVNetwork (https://zoxtvnetwork.com/)
- Recommender Systems
- Natural Language Processing
- The technology advancement in E-commerce have flooded enormous amount of data in the cyberspace. There exist a dire need of proposing effective solutions to filter all the relevant data among the huge pool of disorganized data for users to select the most suitable item among the available items collection. Recommender Systems facilitates the users in selection of items, products or information of users' interest from a large amount of data available on the cyberspace. Recommender systems uses data mining techniques along with prediction algorithms to accomplish the task of providing recommendations. The proposed research work presents a comprehensive survey on existing state-of-the-art recommender systems. This paper presents the classification of recommender systems among content-based, collaborative, demographic, knowledge-based, and hybrid techniques. The proposed work focuses on providing a comprehensive overview of the recommender systems in healthcare. We have proposed a hybrid recommender system for healthcare. The reported results of our proposed system is also presented. This paper also presents the comparison of the proposed system with existing state-of-the-art.*