Beyond one shot recommendations: The seamless interplay of environmental parameters and Quality of recommendations for the best fit list

Abstract

The Knowledge discovery tools and techniques are used in an increasing number of scientific and commercial areas for the analysis and knowledge processing of voluminous Information. Recommendation systems are also one of Knowledge Discovery from databases techniques, which discovers best fit information for appropriate context. This new rage in Information technology is seen in area of E-commerce, E-Learning, and Bioinformatics, Media and Entertainment, electronics and telecommunications and other application domains as well. Academics, Research and Industry are contributing into best-fit recommendation process enrichment, thereby making it better and improvised with growing years. Also one can explore in depth for qualitative and quantitative analysis of E-World Demand and Supply chain with help of recommendation systems. Lot has been talked about effective, accurate and well balanced recommendations but many shortcomings of the proposed solutions have come into picture. This Paper tries to elucidate and model Best Fit Recommendation issues from multidimensional, multi-criteria and real world’s perspectives. This Framework is Quality Assurance process for recommendation systems, enhancing the recommendation quality. The proposed solution is looking at various dimensions of the architecture, the domain, and the issues with respect to environmental parameters. Our goal is to evaluate Recommendation Systems and unveil their issues in quest for the Best Fit Decisions for any application domain and context.