Every year, lakhs of students right from college enter professional life through variousrecruitment activities conducted by the organization. The allotment of projects to the newrecruits, carried out by the HR team of the organization is usually a manual affair. It is a timeconsuming and a tedious process as it involves manually opening each resume and analysing itone by one in order to assign a project. Companies round the globe are leveraging the power ofartificial intelligence and machine learning to increase their productivity. In this paper, wepresent one such use case wherein artificial intelligence is leveraged by the organisation inallotment of projects to the new recruits. Current machine learning tools help in the allotment ofprojects to a few known popular domains on which the classifier has been trained explicitly. Wetackle the problem with an ensemble learning based voting classifier consisting of 5 individualmachine learning classifiers, voting to classify the profile of the candidate into the relevantdomain. The knowledge extracted from the profiles for which there is no majority consensusamong the individual classifiers is used to retrain the model. The proposed model achieves ahigher accuracy in classifying resumes to proper domains than a standard machine learningclassifier which is solely dependent on the training set for classification. Overall, emphasis islaid out on building a dynamic machine learning automation tool which is not solely dependenton the training data in allotment of projects to the new recruits.
展开▼