Lead Time Forecasting with Machine Learning Techniques for a Pharmaceutical Supply Chain Maiza Biazon de Oliveira 1 a , Giorgio Zucchi 2,3 b , Marco Lippi 4 c , Douglas Farias Cordeiro 5 d , N´ ubia Rosa da Silva 1,6 e and Manuel Iori 4 f 1 Special Academic Engineering Unit, Department of Production Engineering, Federal University of Goi´ as, St. Dr. Lamartine Pinto de Avelar, 1120, 75704020, Catal˜ ao, Goi´ as, Brazil 2 Fondazione Marco Biagi, University of Modena and Reggio Emilia, Largo Marco Biagi 10, 41121 Modena, Italy 3 R&D Department, Coopservice S.Coop.p.A, Via Rochdale 5, 42122 Reggio Emilia, Italy 4 Dipartimento di Scienze e Metodi dell’Ingegneria, University of Modena and Reggio Emilia, Via Amendola 2, Pad. Morselli, 42122 Reggio Emilia, Italy 5 Faculty of Information and Communication, Federal University of Goi´ as, Campus Samambaia, 74690900, Goiˆ ania, Goi´ as, Brazil 6 Institute of Biotechnology, Federal University of Goi´ as, St. Dr. LamartinePinto de Avelar, 1120, 75704020, Catal ˜ ao, Goi´ as, Brazil Keywords: Lead Time Forecasting, Machine Learning, Pharmaceutical Supply Chain. Abstract: Purchasing lead time is the time elapsed between the moment in which an order for a good is sent to a supplier and the moment in which the order is delivered to the company that requested it. Forecasting of purchasing lead time is an essential task in the planning, management and control of industrial processes. It is of particular importance in the context of pharmaceutical supply chain, where avoiding long waiting times is essential to provide efficient healthcare services. The forecasting of lead times is, however, a very difficult task, due to the complexity of the production processes and the significant heterogeneity in the data. In this paper, we use machine learning regression algorithms to forecast purchasing lead times in a pharmaceutical supply chain, using a real-world industrial database. We compare five algorithms, namely k-nearest neighbors, support vector machines, random forests, linear regression and multilayer perceptrons. The support vector machines approach obtained the best performance overall, with an average error lower than two days. The dataset used in our experiments is made publicly available for future research. 1 INTRODUCTION Long waiting times for service interventions are a recurring feature in the health sector, especially for public services. Clearly, timely treatments and drug administrations are crucial factors for improving the quality of healthcare services, and often also for saving the lives of patients, mainly in emergen- cies (Brown et al., 2016; Tetteh, 2019). The delay for medical interventions, whether through medica- tion, diagnosis or surgical procedures, can indeed ag- a https://orcid.org/0000-0002-8981-1314 b https://orcid.org/0000-0002-5459-7290 c https://orcid.org/0000-0002-9663-1071 d https://orcid.org/0000-0002-5187-0036 e https://orcid.org/0000-0003-1982-5144 f https://orcid.org/0000-0003-2097-6572 gravate pathologies, given the possibility of deterio- ration of health conditions over time. Longer wait- ing times for medical intervention can increase read- mission rates as well (Moscelli et al., 2016). Nowa- days, this is even more crucial because of the recent COVID-19 pandemic, which is causing an increase in the number of pharmaceutical products urgently required by the many patients affected by the dis- ease (Harapan et al., 2020). Among other factors, long waiting times for re- ceiving medicines can be associated with delay in the administrative packaging, logistic problems with tracking and delivery (Haugh, 2014) and several other factors that could be outside the control of patients or healthcare professionals. Within this scenario, the analysis and proposition of measures to reduce wait- ing times for all possible related factors is important in healthcare policy guidelines (Moscelli et al., 2016). 634 Biazon de Oliveira, M., Zucchi, G., Lippi, M., Cordeiro, D., Rosa da Silva, N. and Iori, M. Lead Time Forecasting with Machine Learning Techniques for a Pharmaceutical Supply Chain. DOI: 10.5220/0010434406340641 In Proceedings of the 23rd International Conference on Enterprise Information Systems (ICEIS 2021) - Volume 1, pages 634-641 ISBN: 978-989-758-509-8 Copyright c  2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved