Knowledge-Based Organizational Happiness Modeling with a Data-Driven Approach: Grounded Theory and Data Mining

The current research was conducted by designing the knowledge-based organizational satisfaction modeling with a data-driven approach using a qualitative and quantitative method of grounded theory and data mining techniques. The data was taken from in-depth and semi-structured interviews with 25 general managers of social security insurance departments in the provinces of the country, based on purposeful sampling. The validity of the research data was checked and confirmed by going back to the participants and external auditors. In the data mining section, registered data and the organization's database were used. Using the data recorded in the Clementine software, the happiness and unhappiness of the employees in the organization were categorized. The results showed that the model of organizational happiness in the social security organization was identified at three levels, group, individual and organization, including causal factors, intervenors, platforms, strategies and finally consequences. Also, the status of employees was determined based on the proposed model of happiness according to the collected data. Finally, the data mining model showed classification with 66% accuracy for happy and unhappy employees. The human resource management approach based on organizational data leads to correct decision making in organizational performance. The more transparent the collected data is, the more accurately the state of the organization can be predicted. Also, based on the proposed model and implementation in the form of data mining, it is possible to estimate the number of happy employees.