ABSTRACT

Recruitment of the most appropriate employees and their retention are the immense challenges for the HR department of most of the industries. Every year IT companies recruit fresh graduates through their campus selection programs. Usually industries examine the skills of the candidate by conducting tests, group discussion and number of interviews. This process requires enormous amount of effort and investment. During each phase of the recruitment process, candidates are filtered based on some performance criteria. The recruitment process of an industry differs each year based on their requirement traits and the process and criteria changes among the industries. This research focuses on investigating the underlying criteria and tries to capitalize on the existing patterns, to minimize the effort made during the recruitment process. Knowledge about the recruitment process was collected from the domain experts and decision trees were constructed with it to identify superior selection criteria. Most of the machine learning algorithms including decision trees have tainted performance in high dimensional feature space and substantiate significant increase in performance with selected features. In this paper, a novel technique based on Ant Colony Optimization is proposed to identify the attributes that impacts the selection process. The proposed ACO technique assigns heuristic information for the attributes based on the estimated conditional probabilities. Experiments were carried out using the dataset collected from an industry to identify the feature sets that give greater accuracy. Decision trees constructed using the C4.5 algorithm with the set of attributes that influence the recruitment process were used to extract feasible rules after making discussions with the domain experts.