A time-series classification framework for individual-level absenteeism prediction under severe class imbalance

2026-06-30

AI Summary

Existing methods for individual absenteeism prediction struggle to achieve truly prospective modeling and often overlook the temporal dynamics of attendance behavior, leading to limited performance under severe class imbalance. This work addresses these limitations by introducing, for the first time, a time series classification paradigm to this task, explicitly separating historical attendance sequences from future absenteeism labels to establish a genuinely forward-looking predictive framework. We propose an automatic calibration strategy for Binary Focal Loss based on the imbalance ratio ρ and demonstrate that Geometric Mean (G-Mean) loss enables adaptive, hyperparameter-free optimization. Experimental results across LSTM, CNN, and LSTM-FCN architectures show that LSTM-FCN combined with the proposed loss functions achieves approximately 80% balanced accuracy on the test set, with Binary Focal Loss yielding a specificity of 0.813 and balanced accuracy of 0.888—performance comparable to that of G-Mean.

Abstract

Staff absenteeism imposes substantial operational costs in high-demand work environments such as healthcare, emergency services, meat processing, construction, and courier and delivery services, where proactive workforce planning depends on reliable individual-level absence prediction. Existing regression and classification approaches share a structural limitation; they map features observed at time t to labels at the same time t, reproducing already-realised outcomes rather than predicting future events, and discard the sequential behavioural structure inherent in individual attendance histories. We propose a Time Series Classification (TSC) framework that separates historical attendance sequences from future absence labels, enabling genuinely proactive prediction. Due to the lack of public longitudinal attendance data, we construct a reproducible simulated dataset calibrated to the UCI dataset. We analyse Binary Focal Loss (BFL) and Geometric Mean (G-Mean) loss under severe class imbalance using only the imbalance ratio $ρ$. For BFL, the initial gradient ratio is $ρα/(1-α)$, implying the balanced weight $α= 1/(1+ρ) \approx 0.023$. Experiments show that performance is governed mainly by $α$, with BFL achieving specificity 0.813 and balanced accuracy 0.888, comparable to G-Mean. Unlike BFL, G-Mean adapts automatically without parameter calibration. Among three deep learning architectures evaluated, Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and the hybrid LSTM-Fully Convolutional Network (LSTM-FCN), the LSTM-FCN delivers strong precision and specificity. Stable performance is obtained with batch sizes >= 64 and window sizes between 40-80 days, yielding balanced accuracy of approximately 80% on held-out test data.

Problem

• absenteeism prediction
• class imbalance
• time-series classification
• proactive workforce planning
• individual-level prediction

Innovation

• Time Series Classification
• Class Imbalance
• Binary Focal Loss
• LSTM-FCN
• Proactive Absenteeism Prediction