Machine Learning Development Audit Framework: Assessment and Inspection of Risk and Quality of Data, Model and Development Process
- The usage of machine learning models for prediction is growing rapidly and proof that the intended requirements are met is essential. Audits are a proven method to determine whether requirements or guidelines are met. However, machine learning models have intrinsic characteristics, such as the quality of training data, that make it difficult to demonstrate the required behavior and make audits more challenging. This paper describes an ML audit framework that evaluates and reviews the risks of machine learning applications, the quality of the training data, and the machine learning model. We evaluate and demonstrate the functionality of the proposed framework by auditing an steel plate fault prediction model.
Download full text files
Additional Services
Statistics
| Author: | Jan StodtORCiDGND, Christoph ReichORCiDGND |
|---|---|
| URN: | https://urn:nbn:de:bsz:fn1-opus4-77950 |
| URL: | https://publications.waset.org/10011898/pdf |
| Parent Title (English): | International Journal of Computer and Information Engineering |
| Document Type: | Article (peer-reviewed) |
| Language: | English |
| Year of Completion: | 2021 |
| Release Date: | 2021/12/13 |
| Tag: | Assessment; Audit; Machine learning; Metrics |
| Volume: | 15.2021 |
| Issue: | 3 |
| First Page: | 187 |
| Last Page: | 193 |
| Open-Access-Status: | Open Access |
| Licence (German): |  Creative Commons - CC BY - Namensnennung 4.0 International |