Understanding the Indian labour market: A data-centric approach

India produces 1.5 million engineers every year. Identifying the significant factors that influence the salary and the jobs these engineers are offered can help us understand the inefficiencies or skill gaps in the labour market, which will be extremely useful for policy making and constructive interventions. Predictive modelling of salary was performed using different machine learning techniques on a data set that included both employee profiles and their employment outcomes. Decision tree analysis, feature analysis, correlation analysis and t-test were performed to identify the significant factors that influenced the annual salary offered to a candidate. Visualizations generated based on employee salary, designation and job city revealed interesting insights.