FMCG DISTRIBUTOR SALES ANALYTICS AND PREDICTION

Abstract

Employee satisfaction is an important factor in maintaining a productive, engaged, and stable workforce. Organizations collect large amounts of employee-related data, including salary, workload, working hours, job role, department, performance, training, and work-life balance. Analyzing this information can help organizations understand employee experiences and identify patterns associated with satisfaction. The Employee Satisfaction Score Prediction system is developed to analyze employee data and predict satisfaction scores using data analytics and Machine Learning techniques. The system processes attributes such as department, job role, salary, experience, workload, working hours, performance rating, training participation, and satisfaction score. Data preprocessing techniques are applied to handle missing values, duplicate records, inconsistent formats, and invalid data. The system performs exploratory and statistical analysis to understand the factors associated with employee satisfaction. Important metrics such as average satisfaction score, satisfaction distribution, department-wise satisfaction, role-wise satisfaction, workload impact, and experience-based satisfaction are calculated. Interactive dashboards display these insights using KPI cards, charts, graphs, tables, and filters. The prediction module uses Machine Learning algorithms to predict an employees satisfaction score or classify satisfaction into categories such as low, medium, and high. Historical employee data is used to train the model, while suitable evaluation metrics are applied to measure prediction performance. The system can therefore provide analytical and predictive insights from available HR data. Overall, the proposed system combines HR analytics, employee satisfaction analysis, data visualization, and predictive modeling in a single platform. It can help HR teams understand satisfaction patterns and analyze workplace factors using historical data. Future enhancements can include real-time employee surveys, sentiment analysis, personalized recommendations, attrition-risk analysis, and automated HR alerts.