DESKTOP BASED RECOMMENDATION SYSTEM FOR CAMPUS RECRUITMENT USING MAHOUT

Abstract

Data mining is the process of posing queries and extracting patterns, often previously unknown from large quantities of data using pattern matching or other reasoning techniques. This project presents a Desktop Based Recommendation System for Campus Recruitment Using Mahout, which can help college placement office to match the company’s criteria with students’ eligibility. This will reduce the need of human intervention. This system automates the activities of placement cells in colleges. Our main focus is on profile matching. The eligible candidates among all will be matched with company’s criteria. For doing this we will use Mahout’s Naïve Bayes Classification algorithm Based on profile similarity degree, the preference lists of companies and students are calculated, which serves as the input of two-sided matching. The new system embedding SMS-based interaction can raise the matching degree, shorten recruiting period and reduce cost. Furthermore, this recommendation service not only is applicable in the field of campus recruitment, but also can provide a framework for the field of mobile business with the extension to other domains such as hospital-intern and college-student matching and recommendation.