Applications of deep learning into supply chain management: a systematic literature review and a framework for future research Artificial Intelligence Review

Finally, product market share is predicted utilizing a consumer selection mathematical model, and a nonlinear constraint programming model is solved to calculate the best price. Figure 5 shows the yearly trend of using keywords with the most growth in appearance. However, we can see two keywords referring to the convolutional neural networks, the second and the fifth keywords. The second keyword, “Convolutional neural network” has not been found until the year 2019 in the papers and then found in 6 and 10 papers in 2020 and 2021 respectively and the fifth keyword, “Neural network CNN” reached 7 in 2021. The other keywords with the most growth are “Supply chain management” and “Supply chain sales”, both of them appeared in 6 papers in the year 2021. It can be concluded that the DL methods have been recently used in the sales area more than the last years.

Customer service KPIs include on-time delivery, damage-free delivery, and fill rate, which measures the percentage of customer orders that are filled at first shipment. It’s important for manufacturers to benchmark their KPIs against industry standard results. Industry groups and analyst firms can provide manufacturing-specific benchmarks; banks can provide financial benchmarks. The job of a supply chain planner is to align production, storage, and transportation with product demand to ensure the right amount of inventory is available at the right time.

The Growing Importance of Supply Chain Optimization

By considering multiple variables and constraints, ANNs can identify the most efficient routes, allocate resources effectively, and reduce costs. Furthermore, ANNs can identify anomalies as well as abnormalities in supply chain data, such as unexpected demand patterns, quality issues and disruptions in logistics operations in order to minimize their impact on the supply chain. ANNs can also analyze supplier performance data, including quality, delivery times and pricing in order to assess the reliability and effectiveness of suppliers. This information can support decision-making processes in supplier evaluation and selection processes. Moreover, ANNs can continuously monitor supplier performance, raising alerts for deviations from predefined criteria to provide safe and secure supply chain in part production processes.

Thus, productivity of part manufacturing can be enhanced by promoting the supply chain management using the artificial neural networks. Machine learning (ML) has emerged as a powerful tool in supply chain management (SCM), enabling organizations to accomplish valuable insights from numerous data and attain informed decisions. This machine learning supply chain optimization paper presents an inclusive review of the recent advancements and applications of ML in SCM. The objective is to provide a holistic understanding of how ML techniques are being utilized to enhance various aspects of supply chain operations. The review begins by outlining the fundamental concepts of ML and its relevance to SCM.

ASCM Insights

Nti et al. (2021) focused on artificial intelligence (AI) algorithms and their applications in the fields of engineering and manufacturing. Their results demonstrated that fault detection, manufacturing cost and energy consumption, and autonomous computing and driving are the most studied problems using AI tools. Kotsiopoulos et al. (2021) described the frequently used machine learning and DL algorithms in the industry 4.0 era, focusing on their use in the smart manufacturing and the smart grid field. Wang et al. (2018) comprehensively reviewed DL techniques, their pros and cons, and their applications in smart manufacturing. Even though there are other reviews on supply chain and machine learning, some areas remain unexploited.

Based on these issues, we provide insights for managers, interesting research areas for future research directions for SCM researchers, and application insight for SCM practitioners. Sales forecasting A sales forecast is an estimate based on previous sales performance and a study of anticipated market circumstances (Gahirwal 2013). DL algorithms have also been applied for sales forecasting because of the ability of these methods to effectively consider the patterns and context-specific non-linear relationships between critical factors (Liu et al. 2020). Weng et al. (2019a) designed a hybrid model to forecast long-term sales of different products and used a grocery sales data set to train their model. Liu et al. (2020) proposed a DL-based model to develop a sales forecasting and analysis system.

Conditional Restricted Boltzmann Machine (CRBM), and Factored Conditional Restricted Boltzmann Machine (FCRBM) are two methods derived from RBM. In the CRBM the RBM is extended by including a conditional history layer (Mnih et al. Conditional Restricted Boltzmann Machines for Structured Output Prediction, 2012). FCRBM (Taylor et al. 2011) is constructed by adding styles and the concept of factored, multiplicative, three-way interactions to the CRBM (Mocanu et al. 2016). The authors Mocanu et al. (2016) investigated the use of CRBM and FCRBM for time series-based forecasting of the energy consumption of individual buildings.