This paper proposes a novel forecasting method that combines the deep learning method – long short-term memory (LSTM) networks and random forest (RF). The proposed method can model complex relationships of both temporal and regression type which gives it an edge in accuracy over other forecasting methods. We evaluated the new method on a real-world multivariate dataset from a multi-channel retailer. We benchmark the forecasting performance of the new proposition against neural networks, multiple regression, ARIMAX, LSTM networks, and RF. We employed forecasting performance metrics to measure bias, accuracy, and variance, and the empirical evidence suggests that the new proposition is (statistically) significantly better. Furthermore, our method ranks the explanatory variables in terms of their relative importance. The empirical evaluations are replicated for longer forecasting horizons, and online and offline channels and the same conclusions hold; thus, advocating for the robustness of our forecasting proposition as well as the suitability in multi-channel retail demand forecasting.

Operations and supply chain management encompasses a vast domain and hence provides a myriad of opportunities for huge voluminous data generated from various sources in real time. Such huge data having the requisite properties of big data can be utilised to gain critical and fundamental insights towards optimising the operations and supply chain and thus making effective and efficient decisions. In the recent years, research interest in big data has increased substantially and therefore researchers and practitioners have also tried to tap the capabilities of big data to optimise operations and supply chain management. In this paper, the literature relating to the integration of big data with operations and supply chain management is reviewed. In particular, reviewing past work is primarily focused on three key areas of the operations and supply chain management, namely manufacturing, procurement and logistics where big data has been applied. In addition to reviewing past literature, paper also proposes application of big data in operations and supply chain management.

Purpose: The purpose of this paper is to identify the Industry 4.0 barriers to achieve circular economy (CE). The study focuses on exploring the link between Industry 4.0 and CE. This leads to the implementation of integrated Industry 4.0-CE and attainment of sustainable production and consumption through analyzing the technological benefits of Industry 4.0. Design/methodology/approach: Industry 4.0 barriers are identified from literature review and discussions with industry experts. Here, the interpretive structural modeling (ISM) technique is applied to develop the contextual relationship among the barriers and to identify the prominent barriers hindering the CE implementation. Findings: The ISM hierarchical model and Matriced’ impacts croised-multiplication applique’ and classment analysis illustrate that the digitalization process and the semantic interoperability possess high driving power and low dependence. These barriers require keen attention to play a significant role in improving resource efficiency and sustainability, and absence of these barriers may not drive other barriers for CE. Apart from these barriers, cyber-physical systems standards and specifications, sensor technology and design challenges are also the most influential Industry 4.0 barriers for achieving CE. Practical implications: The findings provide an opportunity for industry practitioners to explore the most driving Industry 4.0 barriers. The study confirms that integrated Industry 4.0-CE will maintain sustainable operations management by optimizing the production and consumption patterns. It will also provide an opportunity of customization where customers and products interact and can monitor the performance of the operations through the Internet of Things sensors. Originality/value: The study provides integration of Industry 4.0 challenges to implement CE. However, the integration of the two burgeoning fields is still very scarce and lacks in adopting the technological benefits of the integrated Industry 4.0-CE.