Lift and Shift of Model Code Using Machine Learning Microservices with Generative AI Mapping Layer in Enterprise SaaS Applications

Lift and Shift of Model Code Using Machine Learning Microservices with Generative AI Mapping Layer in Enterprise SaaS Applications

연구 분야: Software Development

학회: International Conference on Machine Learning and Soft Computing

Prior research demonstrated with the Minerva platform that there is a need for easy-to-do machine learning (ML) frameworks. Additionally, SaaS applications are closely related when they form an application suite, which brings forth the need for an ML framework that can facilitate the “lift and shift” of ML model code in similar needs in multiple enterprise applications in a suite. This study recommends a portable ML microservice framework, Minerva (also known as contain second generation), a microservices-based container framework for Applied Machine Learning, as an efficient way to modularize and deploy intelligent microservices in both traditional “legacy” SaaS application suites and cloud environments, especially in the enterprise domain. This study identifies that there is an impetus to innovate quickly for machine learning features in enterprise SaaS applications. The study highlights the real-world implementation of Minerva for “lift and shift,” doubling innovation speed with the same resources. It evaluates ML model code reusability across applications, resulting in 1.15 to 2X faster adoption compared to previous methods in a marketing application suite. Secondly, while a layered design accelerated innovation through porting existing models to related business suites, generative AI methods, while promising, have not yet yielded significant gains with smaller models already optimized with no code solutions.