Designing a Data Mining Model to Predict Human Resource Productivity in Food Industry Companies: A Case Study in Shahrood

This study aims to design a data mining model to predict human resource productivity in the food industry using data mining techniques. The research seeks to identify the most important factors affecting productivity and compare the performance of different algorithms in its prediction. This applied research was conducted as a survey-case study in a food production company in Shahrood, Iran. The statistical population included all employees of this company (۱۲۵ people), and the required data were extracted from personnel files, attendance systems, and performance evaluations. The variables examined included demographic characteristics (age, education), occupational factors (work experience, contract type), training (training hours), and behavioral factors (absenteeism, tardiness). Random Forest and Support Vector Machine algorithms were used for data analysis in the Python environment. The results showed that the Random Forest algorithm with ۸۷.۵% accuracy performed better than the Support Vector Machine with ۸۲.۳% accuracy. The most important factors affecting productivity were identified as work experience, number of specialized training hours, and absenteeism rate, respectively. The proposed model can predict human resource productivity with acceptable accuracy and can assist human resource managers in more effective planning. The application of data mining in human resource management opens new horizons for improving organizational productivity.

کلیدواژه ها:

Data Mining ، Human Resource Productivity ، Food Industry ، Random Forest