Machine Learning in Logistic: Scoping Review

Background: Data has become a critical factor in the success of companies, particularly in logistic Machine learning a key area within artificial intelligence, is increasingly supplementing traditional analytical approaches. Machine learning may rapidly modify logistics management to accommodate varying client expectations, thus improving operational responsiveness. This adaptability is essential in contemporary dynamic market contexts, when conventional solutions may fail due to their rigid characteristics. Methodology: This scoping review utilized two databases, Web of Science (WOS) and Scopus, to explore the characteristics of the published scientific literature on this topic and to uncover emerging themes associated with Machine Learning in logistic. Result: This study identified nine main themes, and twenty-two sub-themes related to the application of Machine Learning in logistics. Machine Learning is frequently utilized in inter-company logistics to improve efficiency with suppliers and consumers, manage internal operations, identify weaknesses, and implement corrective actions swiftly. Conclusion: Machine learning algorithms can predict risks in supply chain networks by analysing historical data and identifying potential disruptions. This predictive capability allows organizations to take proactive measures to mitigate risks, thereby minimizing financial losses and operational failures. This opens opportunities for future research, examine the challenges and potential benefits of use machine learning for small and medium-sized firms (SMEs), particularly in providing logistic service.