Machine learning-based mathematical model for drugs and equipment resilient supply chain using blockchain

The world has been stuck in the prevailing COVID and another pandemic for the last three years which leads to the disruption in the medical equipment, drugs, Liquid Oxygen, and other essential goods supply chain. Essential drugs expire during transportation due to a lack of traceability, transparency, corrupt data, and high documentation works. This mismanagement escalates the disruption and shortages. Meanwhile, blockchain (BC) is the latest cutting-edge technology that comes up with the complete solution to disruption, shortages, fraud, poor quality, burglary in data, lack of transparency, lack of traceability, lack of security, cross-delivery, and adulteration. Therefore, blockchain technology can be seen as an opportunity that introduces resilience to the system. The proposed work focuses on optimising the digital procurement cost for significant supplier selection that keeps transparency, traceability, security, and complete information on the distributed ledger. Here, real-time and other aspects of BC, like authenticity, time, etc., are considered while computing the procurement cost in supplier selection problems. The total cost involved in the digital procurement process hinges on the block's authenticity that comes up through the miner's signals. The probability sampling method is used to generate the data for developing the ML-based model. Machine learning (ML) aggregates the value reported by the miners in real time for developing the authenticity (dependent) variables for supplier selection. Later, this real-time authenticity variable is utilised to formulate the mixed-integer nonlinear programming (MINLP) model for digital procurement problems. This MINLP model reduces the disruption and introduced resilience in the information flow system. Finally, LINGO 19.0 is used for optimising the total cost, and the integrated approach of ML is used for the computation of authenticity factor relationships amongst minors in it.