Exploring Data Analytics in Attendance Systems: Unveiling Machine Learning Techniques, Patterns, Practices, and Emerging Trends

Abstract

Purpose: The research aims to identify patterns and trends in attendance management through the application of reward and punishment systems as innovative solutions for improving employee attendance and well-being.

Methods: This research utilizes a descriptive analysis approach with the application of Machine Learning (ML) techniques to enhance the accuracy of attendance pattern prediction and ML models for the classification of emerging trends and patterns. Research data were obtained through the company's attendance system and divided into two segments (80% for training and 20% for testing) while maintaining a balanced class proportion, then processed using SPSS and Python software with the Scikit-learn library.

Result: The results of the study show that employee attendance is increased from 86.52% to 90.44% when the reward and punishment method is applied to the employee attendance system. Proper reward allocation can increase employee motivation to adhere to work schedules and consistently attend, while punishment tends to lead to lower attendance rates.

Novelty: This research emphasizes the optimization of attendance management through data analytics approaches and the implementation of advanced technology in attendance systems with the application of ML techniques to analyze attendance data comprehensively and detect significant patterns.