Project FMEA for Recognizing Difficulties in Machine Learning Application System Development
Naoshi Uchihira · 2022 Portland International Conference on Management of Engineering and Technology (PICMET) · 2022
Digital Transformation (DX) is spreading across all industries. AI, especially machine learning, is inevitable for effective use of data collected and stored in DX, and systems that utilize machine learning have been developed in various industries and companies. The development of machine learning application systems (MLASs) has many difficulties different from the traditional IT system development. Therefore, software engineering (especially project management) for MLASs becomes one of the most important issues in these days. We classified the difficulties of MLAS development based on various documents and interviews, and created a difficulty map consisting of 12 categories. Unique features of this difficulty map include introduction of relationship between difficulties and the dual MLAS development process (implementation process and exploitation process). Then, we propose a method of expressing and sharing these difficulties among stakeholders based on MLAS Project FMEA (Failure Mode Effect Analysis). The proposed method is evaluated using two illustrative MLA examples.