Preliminary Systematic Literature Review of Machine Learning System Development Process
This work addresses the need for standardized processes in ML system development to improve software quality, though it is incremental as a preliminary review.
The authors conducted a preliminary systematic literature review to standardize machine learning system development processes, analyzing 9 papers to identify key phases, practices, and adaptations of traditional methods.
Previous machine learning (ML) system development research suggests that emerging software quality attributes are a concern due to the probabilistic behavior of ML systems. Assuming that detailed development processes depend on individual developers and are not discussed in detail. To help developers to standardize their ML system development processes, we conduct a preliminary systematic literature review on ML system development processes. A search query of 2358 papers identified 7 papers as well as two other papers determined in an ad-hoc review. Our findings include emphasized phases in ML system developments, frequently described practices and tailored traditional software development practices.