AutoML in the Enterprise: Designing Dynamic Model Selection Engines for Business Decisioning
Keywords:
AutoML, model selection, serverless computing, metadata-driven workflowsAbstract
Complexity and velocity of enterprise data streams is continuously increasing which makes adoption of machine learning (ML) infrastructures that can autonomously optimize predictive performance. The aim of this paper is to present a ideal architecture model for dynamic model selection with the help of AutoML meta-layer which utilizes serverless computing envronment for scalable and cost-efficient deployment.
Downloads
References
L. H. Nguyen, H. X. Nguyen, and D. H. Nguyen, “AutoML: A survey of the state-of-the-art,” IEEE Access, vol. 8, pp. 146508-146523, 2020.
J. H. Chu, C. H. Liu, and R. J. Chen, “A survey of AutoML systems,” International Journal of Machine Learning and Cybernetics, vol. 11, no. 7, pp. 1365-1381, 2020.
D. T. O'Neal, A. J. St. George, and W. P. H. Smith, “Hyperparameter optimization techniques in AutoML,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 583-595, Feb. 2021.
A. R. Azimi, M. G. Kian, and F. M. Sadeghi, “Model selection and training in AutoML: The role of NAS and HPO techniques,” Journal of Artificial Intelligence Research, vol. 70, pp. 121-145, 2020.
M. H. Kwon, S. J. Park, and J. Y. Lee, “Serverless computing: A survey of applications, architectures, and approaches,” IEEE Access, vol. 8, pp. 61743-61763, 2020.
M. Schor and L. K. Williams, “Serverless machine learning pipelines: An overview and use case,” Journal of Cloud Computing, vol. 7, no. 3, pp. 27-41, 2021.
G. A. Grinberg, M. J. Van den Oord, and C. D. Cortes, “Meta-learning approaches for AutoML systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 9, pp. 3779-3793, Sept. 2021.
P. D. J. S. Kim, Y. C. Kim, and D. W. Lee, “Optimizing AutoML pipelines using reinforcement learning techniques,” Journal of Machine Learning Research, vol. 21, pp. 1-15, 2020.
M. G. Alibakhshi, R. K. Mishra, and K. M. X. Zhang, “AutoML-based fraud detection using data mining and machine learning techniques,” IEEE Transactions on Industrial Informatics, vol. 17, no. 3, pp. 2147-2155, Mar. 2021.
J. H. V. Smith, K. W. Johnson, and T. B. Martin, “Deploying AutoML systems at scale: Challenges and solutions in enterprise settings,” Proceedings of the IEEE International Conference on Cloud Computing Technology and Science, pp. 180-187, 2020.
R. B. Green, M. A. S. Maurer, and L. S. P. Wright, “Serverless frameworks for automated model deployment in AI applications,” IEEE Transactions on Cloud Computing, vol. 9, no. 4, pp. 987-996, Jul.-Aug. 2021.
H. H. Lee and T. G. Tan, “Evaluating the performance of AutoML systems for dynamic model selection in real-time applications,” IEEE Access, vol. 9, pp. 25653-25667, 2021.
W. K. Yip, T. S. Y. Choi, and H. K. Tan, “Dynamic machine learning systems: Model selection for adaptive real-time decision-making,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 2, pp. 371-382, Feb. 2021.
L. K. Hwang, F. S. Wu, and W. M. C. Zhou, “Challenges and solutions in continuous model adaptation for AutoML in enterprise systems,” Proceedings of the IEEE International Conference on Big Data, pp. 1358-1365, 2020.
J. S. Lee, S. S. Wang, and C. D. Fu, “A study on improving model selection accuracy in AutoML systems,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 1, pp. 51-62, Jan. 2021.
P. V. Wang, R. S. Lee, and T. A. Shishika, “Optimizing resource allocation for serverless AutoML workflows,” Journal of Cloud Computing: Advances, Systems and Applications, vol. 8, no. 5, pp. 45-58, 2020.
Y. G. Zhang, M. Y. Lee, and S. G. Hsiao, “Integrating AutoML with continuous integration pipelines: Best practices for deployment,” IEEE Software, vol. 38, no. 4, pp. 45-53, Jul.-Aug. 2021.
T. W. X. Coo, D. H. Simpson, and M. Y. F. Wu, “Serverless AutoML systems for automated decision-making in IoT,” IEEE Transactions on Industrial Electronics, vol. 67, no. 6, pp. 4861-4870, Jun. 2020.
P. D. S. Han, B. M. Sharma, and K. L. Chong, “Reinforcement learning for dynamic model selection in enterprise AI systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 8, pp. 2321-2332, Aug. 2021.
M. S. Park, A. L. Hsu, and F. T. Chen, “Enhancing model selection strategies in AutoML systems with federated learning,” Proceedings of the IEEE International Conference on Machine Learning and Applications, pp. 1269-1277, 2020.
