Hybrid demand forecasting: integrating behavioral economics with econometric and machine learning models

2026-03-09T09:45:16+00:00

Accurate demand forecasting is critical for firm-level operational and strategic decisions, yet conventional econometric and machine learning models largely abstract from systematic behavioral distortions in consumer decision-making. Drawing on behavioral demand theory, this study develops and empirically evaluates a hybrid forecasting framework that integrates reference dependence, habit persistence, and attention-based mechanisms into econometric, machine learning, and ensemble demand forecasting models. Using firm-level demand data and a rolling-origin validation design, we compare traditional baseline models with behaviorally augmented specifications across multiple forecast horizons and error metrics. The results show that models incorporating behavioral variables consistently and significantly outperform standard econometric and machine learning benchmarks out of sample. Reference price losses exert a substantially stronger predictive influence than gains, consistent with loss aversion, while habit persistence dominates short-horizon forecasts and attention and sentiment measures contribute most at medium horizons. Further gains are achieved through forecast ensembles that combine behaviorally augmented econometric and machine learning models, indicating complementary strengths in structural discipline and non-linear approximation. These findings demonstrate that behavioral demand mechanisms are not only explanatory but also predictively relevant at the firm level. The study contributes to behavioral demand theory by extending it into an explicitly predictive context, advances forecasting methodology by showing the value of theory-guided feature augmentation, and offers a scalable framework for firms seeking more accurate and behaviorally informed demand forecasts.

Keywords: Behavioral Demand, Econometric Models, Forecast Ensembles, Habit Persistence, Loss Aversion.

Advances in data-driven workplace safety risk prediction systems for preventing occupational injuries

2026-03-26T09:11:08+00:00

This study examines recent advances in data-driven workplace safety risk prediction systems developed to prevent occupational injuries across industrial, construction, healthcare, logistics, and manufacturing environments. Persistent workplace hazards continue to impose major human, operational, and economic costs despite the existence of traditional safety protocols, inspections, and compliance frameworks. Conventional safety management approaches are often reactive, relying on incident reporting after harm has occurred, thereby limiting their capacity to anticipate emerging risks in dynamic work settings. In response, data-driven risk prediction systems have gained prominence as proactive tools for identifying patterns, forecasting unsafe conditions, and supporting timely preventive interventions. These systems integrate data from incident records, near-miss reports, wearable sensors, machine logs, environmental monitoring devices, surveillance systems, and workforce behavior analytics to generate real-time or near-real-time safety intelligence. Advances in machine learning, artificial intelligence, predictive analytics, and Internet of Things technologies have significantly improved the precision, adaptability, and operational relevance of these systems. The study highlights how modern predictive models can detect high-risk activities, estimate injury likelihood, prioritize vulnerable locations, and provide decision support for supervisors, safety managers, and organizational leaders. It further explores the role of dashboards, automated alerts, digital twins, and adaptive control systems in strengthening hazard recognition and response coordination. In addition, the study emphasizes the importance of data quality, human factors, model interpretability, privacy protection, and ethical governance in ensuring that predictive systems remain trustworthy and effective in practical settings. It argues that successful implementation depends not only on technical sophistication but also on organizational readiness, worker engagement, leadership commitment, and integration with broader occupational health and safety management systems. By shifting workplace safety from retrospective analysis to predictive prevention, data-driven systems offer a transformative pathway for reducing injury frequency, enhancing situational awareness, and improving resilience in complex operational environments. The study concludes that advances in predictive safety technologies can substantially strengthen occupational injury prevention when supported by transparent governance, interdisciplinary collaboration, and context-sensitive deployment strategies tailored to the realities of diverse workplaces. These innovations also create opportunities for continuous learning, stronger regulatory compliance, more efficient resource allocation, and safer work cultures that prioritize prevention before incidents escalate into serious harm or long-term occupational health consequences.

Keywords: Workplace Safety, Risk Prediction Systems, Occupational Injuries, Predictive Analytics, Machine Learning, Injury Prevention, Occupational Health and Safety.

Gulf Journal of Advance Business Research

Hybrid demand forecasting: integrating behavioral economics with econometric and machine learning models

Advances in data-driven workplace safety risk prediction systems for preventing occupational injuries