Towards MLOps in Mobile Development with a Plug-in Architecture for Data Analytics

Abstract

Smartphones are increasingly used as universal IoT gateways collecting data from connected sensors in a wide range of industrial applications. With the increasing computing capabilities, they are used not just for simple data aggregation and transferring, but have now become capable of performing advanced data analytics. As AI has become a key element in enterprise software systems, many software development teams rely on dedicated Machine Learning (ML) engineers who often follow agile development practices in their work. However, in the context of mobile app development, there is still limited tooling support for MLOps, mainly due to unsuitability of native programming languages such as Java and Kotlin to support MLrelated programming tasks. This paper aims to address this gap and describes a plug-in architecture for developing, deploying and running ML modules for data analytics on the Android platform. The proposed approach advocates for modularity, extensibility, customisation, and separation of concerns, allowing ML engineers to develop their components independently from the main application in an agile and incremental manner.