International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 171 - Number 1 |
Year of Publication: 2017 |
Authors: Neeraj Khadilkar, Deepali Joshi |
10.5120/ijca2017914966 |
Neeraj Khadilkar, Deepali Joshi . Predictive Model on Employability of Applicants and Job Hopping using Machine Learning. International Journal of Computer Applications. 171, 1 ( Aug 2017), 37-41. DOI=10.5120/ijca2017914966
The rate of rejection of various candidates is rising in spite of abundant job openings. Employability is a set of achievements, understandings and personal attributes that make individuals more likely to gain employment and to be successful in their chosen occupations. It is the ability of the candidate to check whether he/she is capable to gain employment or not. This is an automated effort to predict whether a person is employable or needs more training. This would help in the institutions to assess whether they are producing employable students or not, also this would provide a support for organizations in screening bundles of applications and finding the most suitable ones. Job hopping is another open problem in the industry wherein lots of efforts and resources are invested in the hiring process as well as in grooming the employee .It would be a great help to the employers if they are provided with tool which can predict the job hopping of the employees so that the managers can be prepared for the same. We are providing a solution to both the above stated problems in a novel way. In screening the resumes we use text mining and appropriate weighing in addition to personal attributes of the candidate which helps in improving accuracy of the system also our job hopping module is novice in terms of using text understanding from reviews about the company for hopping prediction. For employability prediction we got the highest accuracy for naïve based with 89% and for predicting whether the employee’s going to quit the job or not we got the highest accuracy for decision tree with 85%.