Establishing a link between employee turnover and withdrawal behaviours: application of data mining techniques

Abstract

Employee turnover is a serious concern in knowledge based organisations. When employees leave an organisation, they carry with them invaluable tacit knowledge which is often the source of competitive advantage for the business. In a rapidly growing sector like the Indian software industry employee turnover poses risk and challenges for organisations. This research explores the relationship of withdrawal behaviours like lateness and absenteeism, job content, tenure and demographics on employee turnover. The unique aspect of this research has been the use of five predictive data mining techniques on a sample data of 150 employees in a large software organisation. The results of the study clearly show a relationship between withdrawal behaviours and employee turnover. Age and marital status emerged as key demographic variables. The findings of this study have implications for both research and practice. There is a need to expand the scope of this research to include multiple organisations and a large sample, which will allow for more robust predictions. For practitioners, it emphasises the need for greater use of models and analytical tools in engaging with human resource strategies and plans, and in particular that HR professionals will need to understand, appreciate and apply such models in future to be able to perform their roles as strategic business partners.