Machine learning and multi-criteria decision-making techniques in recruitment: An empirical study

Today, there are technological developments in many areas. These technological developments pave the way for the recording of big data, the creation of data warehouses, the analysis of these data when necessary, and the making of studies that support decision-making. One of the most frequently used areas of decision-making activity is recruitment. Human resources are the organizational structure that carries out the recruitment process. Failure to match the right employee and the right job causes many problems in organizations. Today, companies generally follow a recruitment strategy that is far from objective qualifications. These subjective methods followed often expose the recruitment process to personal experience. The Multi-Criteria Decision-Making Method is generally used for many sectors and positions in the recruitment process. One of the most widely used Multi-Criteria Decision-Making methods is the AHP method. In this study, criterion weighting for the selection of a blue-collar mechanic of a textile company was made with AHP, which is one of the multi-criteria decision-making methods, and the GBT method, which is one of the machine learning methods. A ranking was made among 10 alternative criteria. The data of the personnel were obtained from the human resources department of the company. The data has been cleaned and turned into quality data. 269 data were subjected to classification algorithms and then the appropriate classification method was determined. Data were analyzed with the RapidMiner package program. With the GBT method, 10 criteria were weighted. Then, the criteria weights weighted with GBT, and the criteria weights found with AHP were compared. This study contributes to the literature as an empirical study using both AHP from Multi-Criteria Decision-Making Methods and GBT from machine learning methods.