Using AI and ML to predict shipment times of therapeutics, diagnostics and vaccines in e-pharmacy supply chains during COVID-19 pandemic

Abstract

PurposeThis paper aims to address the pressing problem of prediction concerning shipment times of therapeutics, diagnostics and vaccines during the ongoing COVID-19 pandemic using a novel artificial intelligence (AI) and machine learning (ML) approach.Design/methodology/approachThe present study used organic real-world therapeutic supplies data of over 3 million shipments collected during the COVID-19 pandemic through a large real-world e-pharmacy. The researchers built various ML multiclass classification models, namely, random forest (RF), extra trees (XRT), decision tree (DT), multilayer perceptron (MLP), XGBoost (XGB), CatBoost (CB), linear stochastic gradient descent (SGD) and the linear Naïve Bayes (NB) and trained them on striped datasets of (source, destination, shipper) triplets. The study stacked the base models and built stacked meta-models. Subsequently, the researchers built a model zoo with a combination of the base models and stacked meta-models trained on these striped datasets. The study used 10-fold cross-validation (CV) for performance evaluation.FindingsThe findings reveal that the turn-around-time provided by therapeutic supply logistics providers is only 62.91% accurate when compared to reality. In contrast, the solution provided in this study is up to 93.5% accurate compared to reality, resulting in up to 48.62% improvement, with a clear trend of more historic data and better performance growing each week.Research limitations/implicationsThe implication of the study has shown the efficacy of ML model zoo with a combination of base models and stacked meta-models trained on striped datasets of (source, destination and shipper) triplets for predicting the shipment times of therapeutics, diagnostics and vaccines in the e-pharmacy supply chain.Originality/valueThe novelty of the study is on the real-world e-pharmacy supply chain under post-COVID-19 lockdown conditions and has come up with a novel ML ensemble stacking based model zoo to make predictions on the shipment times of therapeutics. Through this work, it is assumed that there will be greater adoption of AI and ML techniques in shipment time prediction of therapeutics in the logistics industry in the pandemic situations.

A large-scale real-world comparative study using pre-COVID lockdown and post-COVID lockdown data on predicting shipment times of therapeutics in e-pharmacy supply chains

“…Singh and Soni (2019) presented various ML algorithms to predict order lead time for just-in-time production systems. While Mariappan et al. (2022) demonstrated how shipment time of medical supplies after COVID lockdown can be predicted using ML modeling techniques, this present paper deals with pre-COVID lockdown versus post-COVID lockdown scenarios, datasets, experiments and shows that the proposed approach is robust to curb the pandemic's disruptions by performing a comparative study between real-world pre-COVID lockdown dataset (2.87 million records) and post-COVID lockdown dataset (3.03 million records).…”

Innovations in freight transport: a systematic literature evaluation and COVID implications

“…Recently, Barua et al (2020) investigated ML methods applied to solve problems in international freight transport management and identified a stream of ML studies in forecasting transport demand and its on-time performance and vehicle routing. Given increasing data availability and the adoption of artificial intelligence and ML, Mariappan et al (2022), developed a new ML ensemble stacking-based model to forecast the delivery time in the supply chain of therapeutics, diagnostics and vaccines, which can be applied to other supply chains during pandemics.…”

“…The temporary restrictions of business operations, closure of certain services/organisations, intensification of frontline/emergency services, travel restrictions and all have significant impacts on freight transport (Loske, 2020). While the reduced amount of passenger travel (76% decrease in urban mobility (Aloi et al, 2020)) has had positive impacts on traffic and the environment (Sommer, 2020), the changes in demand for food, medical/ pharmaceutical, household products, combined with sudden changes in the accessibility of raw materials, parts, goods, manufacturing capacities, caused major disruptions in industrial operations (Gray, 2020;Sharma et al, 2020;Mishra et al, 2021), propagated across the supply chains (Herold et al, 2021;Mariappan et al, 2022). A temporary solution has been proposed to manage air cargo (Shaban et al, 2021).…”

Guest editorial: Bridging the research-practice gaps in supply chain management: lessons from COVID-19

“…Finally, we understand that the analytical-based articles have significantly contributed to advancing operations and the supply chain management field (Boyer and Swink, 2008) by solving problems. We accepted some relevant articles that may be useful for the practitioners based on analytical methods (see, Zhang et al , 2021; Paul et al , 2021; Dohale et al , 2021; Abdolazimi et al , 2021; Mariappan et al ., 2022; Banik et al , 2022; Yassine, 2022).…”