The COVID-19 pandemic has been one of the biggest disruptive events of recent decades and has had a global effect on society and the economy. The political regulations resulting from COVID-19 also led to significant changes in physical grocery shopping. However, the specific impact of COVID-19 on consumer satisfaction at the customer end of retail supply chains, i.e., the point-of-sale (PoS), has not yet been addressed. By gathering and analyzing consumer satisfaction data (ratings) and sentiments (evaluation comments) available on the open web, the current study evaluates the impact of COVID-19 on consumer satisfaction at the PoS. Focusing on the five biggest retail chains in Austria, the results show that there was a general and significant decline in consumer satisfaction due to the pandemic. The results also show a high impact of political regulations on consumer satisfaction. Furthermore, the text-mining based analysis of evaluation comments indicate that store layout and facilities, as well as product availability and waiting time had a great impact on consumer satisfaction. In total, over 533,000 consumer satisfaction ratings and over 153,000 textual comments have been analyzed, providing the basis for a comprehensive and sound discussion of the impact of COVID-19 on consumer satisfaction and perceptions. Future research could focus on applying the used data analysis technique and the adapted consumer sentiment dimensions in different settings, such as countries other than Austria or smaller retail chains.

In the realm of retail supply chain management, accurate forecasting is paramount for informed decision making, as it directly impacts business operations and profitability. This study delves into the application of tree-based ensemble forecasting, specifically using extra tree Regressors (ETRs) and long short-term memory (LSTM) networks. Utilizing over six years of historical demand data from a prominent retail entity, the dataset encompasses daily demand metrics for more than 330 products, totaling 5.2 million records. Additionally, external variables, such as meteorological and COVID-19-related data, are integrated into the analysis. Our evaluation, spanning three perishable product categories, reveals that the ETR model outperforms LSTM in metrics including MAPE, MAE, RMSE, and R². This disparity in performance is particularly pronounced for fresh meat products, whereas it is marginal for fruit products. These ETR results were evaluated alongside three other tree-based ensemble methods, namely XGBoost, Random Forest Regression (RFR), and Gradient Boosting Regression (GBR). The comparable performance across these four tree-based ensemble techniques serves to reinforce their comparative analysis with LSTM-based deep learning models. Our findings pave the way for future studies to assess the comparative efficacy of tree-based ensembles and deep learning techniques across varying forecasting horizons, such as short-, medium-, and long-term predictions.

Inter-organizational collaboration is an important aspect of organizational operations. Traditional systems that support organizations in executing these collaborations are inefficient, not inter-operable and insecure. Novel functions provided by blockchain technology yields the potential for addressing problems that affect organizational collaborations by enabling tamper-proof, transparent, and secure systems for the exchange of information between organizations. Still, a proper approach for building blockchain-decentralized applications (DApps) that support inter-organizational collaborations is missing. The DAOM framework addresses this gap by providing a model-driven design approach for building DApps. This paper shows the development of the semantics of the DAOM framework, implementation of the support tool, and the evaluation of the DAOM framework and support tool. We conducted an evaluation to understand the usefulness of the DAOM framework in developing blockchain DApps and the effectiveness of the support tool in producing DAOM diagram models. The evaluation result shows that the framework is useful and applicable for developing DApps for inter-organizational collaborations. Furthermore, evaluation of the tool support shows that DApps can be modelled efficiently and correctly with the implemented enterprise-modelling software.

In recent years, there has been a growing surge of interest in the application of data analytics (DA) within the realm of supply chain management (SCM), attracting attention from both practitioners and researchers. This paper presents a comprehensive examination of recent implementations of DA in SCM. Employing a systematic literature review (SLR), we conducted a meticulous analysis of over 354 papers. Building upon a prior SLR conducted in 2018, we identify contemporary areas where DA has been applied across various functions within the supply chain and scrutinize the DA models and techniques that have been employed. A comparison between past findings and the current literature reveals a notable upsurge in the utilization of DA across most SCM functions, with a particular emphasis on the prevalence of predictive analytics models in contemporary SCM applications. The findings of this paper offer a detailed insight into the specific DA models and techniques currently in use across various SCM functions. Additionally, a discernible increase in the adoption of mixed or hybrid DA models is observed. However, several research gaps persist, including the need for more attention to real-time DA in SCM, the integration of publicly available data, and the application of DA to mitigate uncertainty in SCM. To address these areas and guide future research endeavors, the paper concludes by delineating six concrete research directions. These directions offer valuable avenues for further exploration in the field.