Author:
Vela Daniel,Sharp Andrew,Zhang Richard,Nguyen Trang,Hoang An,Pianykh Oleg S.
Abstract
AbstractAs AI models continue to advance into many real-life applications, their ability to maintain reliable quality over time becomes increasingly important. The principal challenge in this task stems from the very nature of current machine learning models, dependent on the data as it was at the time of training. In this study, we present the first analysis of AI “aging”: the complex, multifaceted phenomenon of AI model quality degradation as more time passes since the last model training cycle. Using datasets from four different industries (healthcare operations, transportation, finance, and weather) and four standard machine learning models, we identify and describe the main temporal degradation patterns. We also demonstrate the principal differences between temporal model degradation and related concepts that have been explored previously, such as data concept drift and continuous learning. Finally, we indicate potential causes of temporal degradation, and suggest approaches to detecting aging and reducing its impact.
Publisher
Springer Science and Business Media LLC
Reference40 articles.
1. Hilpisch, Y. Artificial Intelligence in Finance, O'Reilly (2020).
2. Al-Blooshi, L. & Nobanee, H. Applications of artificial intelligence in financial management decisions: A mini-review. SSRN Electron. J. https://doi.org/10.2139/ssrn.3540140 (2020).
3. Lee, J., Davari, H., Singh, J. & Pandhare, V. Industrial artificial intelligence for industry 4.0-based manufacturing systems. Manuf. Lett. 18, 20–23 (2018).
4. Jha, K., Doshi, A., Patel, P. & Shah, M. A comprehensive review on automation in agriculture using artificial intelligence. Artif. Intell. Agric. 2, 1–12 (2019).
5. Choy, G. et al. Current applications and future impact of machine learning in radiology. Radiology 218, 318–328 (2018).
Cited by
41 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献