Deconstructing risk factors for predicting risk assessment in supply chains using machine learning

Risk management is an ongoing process that includes several stages of mapping and identification, analysis, and evaluation, planning, and implementation to reduce risks and ensure ongoing control. Risk management along the supply chains has become more significant in recent years due to an increased complexity of the relationships between components in the chain as well as various disruptions such as climate change, COVID-19, or geo-political scenarios. The current literature alongside the increase in complexity and frequency of risk events, leads us to the single, most prominent challenge in risk management today: the auditor's subjectivity in determining the risk levels. Simply stated, two different auditors may assess a given situation differently due to their specific history and experience. Specifically, it seems to be extremely difficult to find cases in which different auditors, working on the same organization, made the same risk assessment. With that in mind, this research aims to reduce the human subjectivity bias and reach a risk evaluation that is as objective as possible, by using the machine learning approach. For this aim the paper introduces a new risk assessment framework based on factors analysis and artificial neural network as the predictive model. We first introduced a new approach of deconstructing the risk factors into their basic elements and analyzing them as a feature vector. Next, we collected unique, real-world data of risk surveys and audit reports from 60 industrial companies of various industries (from plastic and metal factories to logistic and medical devices companies). Lastly, we constructed a neural network to predict the risk levels of operational processes in the industry. We trained our model on 42 samples and managed to achieve a R2 score of 0.9 on the test set of 18 samples. Our model was validated and managed to predict the risk accuracy with R = 0.95 in accordance with the human auditor results.