PREDICTIVE ANALYTICS FOR WORKFORCE REDUCTION IN MULTINATIONAL CORPORATIONS: A LOGISTIC REGRESSION APPROACH

Abstract: Corporate workforce restructuring has become one of the defining business challenges of our era. Over the past several years, multinational corporations across technology, finance, and manufacturing have carried out large-scale layoffs driven by a mix of macroeconomic headwinds, rapid automation, shrinking profit margins, and rising debt loads. Yet despite the frequency of these events, most organisations still lack any reliable early-warning system to flag layoff risk before decisions are locked in. This study introduces a data-driven approach to predicting corporate layoff events. Using a synthetic dataset of 1,500 firm-year observations spanning 2020 to 2026, we built a logistic regression model that draws on financial indicators, operational metrics, and macroeconomic data. The model was trained, validated through stratified cross-validation, and tested against a comprehensive set of classification metrics. We engineered several composite features including revenue decline flags, high-automation indicators, debt-to-equity thresholds, and an overall risk score that meaningfully improved predictive accuracy. We then applied the trained model to estimate layoff probabilities for ten prominent global companies in 2025–2026. The model achieved a ROC-AUC of around 0.82, with well-balanced precision and recall. Our aim is to offer a practical, reproducible methodology that organisations and policymakers can genuinely use for early workforce risk assessment.

Keywords: corporate layoffs, logistic regression, workforce analytics, predictive modelling, MNC risk assessment, automation adoption, financial indicators, ROC-AUC.