Towards Guidelines for Assessing Qualities of Machine Learning Systems
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Nowadays, systems containing components based on machine learning (ML) methods are becoming more widespread. In order to ensure the intended behavior of a software system, there are standards that define necessary quality aspects of the system and its components (such as ISO/IEC 25010). Due to the different nature of ML, we have to adjust quality aspects or add additional ones (such as trustworthiness) and be very precise about which aspect is really relevant for which object of interest (such as completeness of training data), and how to objectively assess adherence to quality requirements. In this article, we present the construction of a quality model (i.e., evaluation objects, quality aspects, and metrics) for an ML system based on an industrial use case. This quality model enables practitioners to specify and assess quality requirements for such kinds of ML systems objectively. In the future, we want to learn how the term quality differs between different types of ML systems and come up with general guidelines for specifying and assessing qualities of ML systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Review on Evaluation Metrics for Data Classification Evaluations
M, H., & M.N, S. (2015) · International Journal of Data Mining & Knowledge Management Process · doi:10.5121/ijdkp.2015.5201 · Cited by 2,693 · cited 1×
“For example, for classification tasks, the goodness of fit can be measured by accuracy, precision, recall, f-score, etc. [18], but for clustering, other measures are needed [19].”
BackgroundInherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943 · cited 1×
“Some metrics might not be compatible with one another, as is the case, for example, for fairness measures [20, 21].”
BackgroundInherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
Machine Learning Testing: Survey, Landscapes and Horizons
Zhang, J. M., Harman, M., Ma, L., & Liu, Y. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2962027 · Cited by 897
Leakage in data mining: Formulation, detection, and avoidance
Kaufman, S., Rosset, S., Perlich, C., & Stitelman, O. (2012) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2382577.2382579 · Cited by 791
Lwakatare, L. E., Raj, A., Bosch, J., Olsson, H. H., & Crnkovic, I. (2019) · Lecture Notes in Business Information Processing · doi:10.1007/978-3-030-19034-7_14 · Cited by 214 · cited 1×
“In the last years, more case studies and literature reviews have been conducted to assess the challenges perceived by developers of ML components, as well as their processes and best practices [1, 3, 16, 17].”
BackgroundHow does Machine Learning Change Software Development Practices?
Wan, Z., Xia, X., Lo, D., & Murphy, G. C. (2020) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2937083 · Cited by 181 · cited 2×
“Developing and operating ML systems raises new challenges in comparison to “classical” software engineering [1, 2].”
BackgroundLeakage in data mining: formulation, detection, and avoidance
Kaufman, S., Rosset, S., & Perlich, C. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020496 · Cited by 137
Engaging the ethics of data science in practice
Barocas, S., & Boyd, D. (2017) · Communications of the ACM · doi:10.1145/3144172 · Cited by 86 · cited 1×
“ation tasks, the cost of a false-positive may not be the same as the cost of a falsenegative. Some metrics might not be compatible with one another, as is the case, for example, for fairness measures [20, 21]. Fig. 1. The availability of ground truth data (labels) has a direct impact on the analysis or training method…”
Cited by
Giray, G. (2021) · Journal of Systems and Software · doi:10.1016/j.jss.2021.111031 · Cited by 187
Taxonomy of Machine Learning Safety: A Survey and Primer
Mohseni, S., Wang, H., Xiao, C., Yu, Z., Wang, Z., & Yadawa, J. (2023) · ACM Computing Surveys · doi:10.1145/3551385 · Cited by 53
Artificial intelligence for dementia drug discovery and trials optimization
Doherty, T., Yao, Z., Khleifat, A. A. L., Tantiangco, H., Tamburin, S., Albertyn, C., Thakur, L., Llewellyn, D. J., Oxtoby, N. P., Lourida, I., et al. (2023) · Alzheimer's & Dementia · doi:10.1002/alz.13428 · Cited by 48
Navigating the EU AI Act: A Methodological Approach to Compliance for Safety-critical Products
Kelly, J., Zafar, S. A., Heidemann, L., Zacchi, J.-V., Espinoza, D., & Mata, N. (2024) · 2024 IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00179 · Cited by 30
“The extent to which the product or system protects the privacy and handles sensitive information of the stake-holders involved (users, people in training examples).”
BackgroundInfluentialDeveloping and Operating Artificial Intelligence Models in Trustworthy Autonomous Systems
Martínez-Fernández, S., Franch, X., Jedlitschka, A., Oriol, M., & Trendowicz, A. (2021) · Lecture Notes in Business Information Processing · doi:10.1007/978-3-030-75018-3_14 · Cited by 22
Metadata
- Authors
- Siebert, J., Joeckel, L., Heidrich, J., Nakamichi, K., Ohashi, K., Namba, I., Yamamoto, R., & Aoyama, M.
- Venue
- Communications in Computer and Information Science
- Publisher
- Springer International Publishing
- Published
- 2020
- Pages
- 17-31
- ISSN
- 1865-0929 (ISSN-L)
- 1865-0937
- OpenAlex
- W3080999680
- Cited by
- 58
- References
- 9
- FWCI
- 8.14
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.