A Data Modeling Method for Machine Learning Systems
Wenting Shao, Xi Wang · 2022
Machine learning (ML) technology is advancing rapidly but the existing development process lacks standardized process, and the quality of machine learning system development is difficult to guarantee. Requirement modeling is an important method to ensure software quality. Data is the key factor to distinguish machine learning systems (MLS) from traditional systems. However, there is no effective modeling method and supporting tool to effectively guide researchers in data modeling for MLS. To address this problem, this paper introduces a two-layer data requirements modeling method for MLS and develops a supporting tool for this method to help users better model data. In order to better illustrate our data requirements modeling method and the supporting tool, we give an example of a self-driving system as the case study.