Fake news on Facebook and their impact on supply chain disruption during COVID-19.

Social media (SM) fake news has become a serious concern especially during COVID-19. In this study, we develop a research model to investigate to what extent SM fake news contributes to supply chain disruption (SCD), and what are the different SM affordances that contribute to SM fake news. To test the derived hypotheses with survey data, we have applied partial least square based structural equation modelling (PLS-SEM) technique. Further, to identify how different configurations of SC resilience (SCR) capabilities reduce SCD, we have used fuzzy set qualitative comparative analysis (fsQCA). The results show that SM affordances lead to fake news, which increases consumer panic buying (CPB); CPB in turn increases SCD. In addition, SM fake news directly increases SCD. The moderation test suggests that, SCR capability, as a higher-order construct, decreases the effect of CPB on SCD; however, neither of the capabilities individually moderates. Complimentarily, the fsQCA results suggest that no single capability but their three specific configurations reduce SCD. This work offers a new theoretical perspective to study SCD through SM fake news. Our research advances the knowledge of SCR from a configurational lens by adopting an equifinal means towards mitigating disruption. This research will also assist the operations and SC managers to strategize and understand which combination of resilience capabilities is the most effective in tackling disruptions during a crisis e.g., COVID-19. In addition, by identifying the relative role of different SM affordances, this study provides pragmatic insights into SM affordance measures that combat fake news on SM.

Incorporating causality in energy consumption forecasting using deep neural networks.

Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems.