Abstract

These days Career and Domain options have always been a very big ambiguous decision-making process for many prospective aspirants. Many aspirants make substantial domain changes very late in their career which may result in drastic effects on their career as well as their financial status. Many reports suggested that companies have suffered huge losses because of making wrong choices regarding the domain and employee interest. Hence providing a common platform early in the education sector for both the aspirants as well as companies that would provide appropriate domain suggestions for aspirants as well as right employee choices for companies would be highly beneficial that could help in generating better results when compared to the traditional ways of career choices employment. In this research, we are proposing a recommender system based model that would bridge the gap and help in formulating future needs

Highlights

  • Over the last few years, many technologies have taken over the IT Industry making several changes that are permanently renounced and are still having a huge impact in the present day scenario

  • The proposed model is a machine learning model that generates recommendations’ using recommender systems concept of machine learning by analyzing the huge amounts of data assembled using big data technologies

  • Results that have generated from the model can be reused for the selfimprovement of the model by rolling out the feedback of a particular recommendation that has been previously made by the model. This data could help the model in rectifying wrong recommendations and provide highly accurate decisions in the recommendations. The approach of this model has a huge impact on the educational institutions and the corporate sector of today's highly competitive world

Read more

Summary

Introduction

Over the last few years, many technologies have taken over the IT Industry making several changes that are permanently renounced and are still having a huge impact in the present day scenario. We use collaborative filtering because of the main drawbacks that the proposed model consists which are, most users do not provide evaluation and user matrix can result in great sparsity Another such issue is for a given metric there is no previous data that particular metric could result in not being recommended to any user by using collaborative and content-based filtering we can oversee these issues. By input on significance, it is conceivable to make a profile for new clients, taking care of the first rater issue [5] Using these technologies and algorithm we build the overall model that can input and output data. A user-interactive platform built using Web Design & Development technologies is very important for the user experience and user interaction that could help in the improvement of data generated daily

Prevalent System and Need for Change
Proposed Model
Phase 1
Phase 2
Phase 3
Future Scope and Prospective Advantages
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call