Deconstructing Risk Factors for Predicting Risk Assessment in Supply Chains Using Machine Learning
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".