Towards Improved Research Methodologies for Industrial AI: A case study of false call reduction
This work addresses the gap between academic AI research and practical industrial needs, highlighting incremental improvements in methodology for applied AI researchers and practitioners.
The paper tackles the problem of whether current AI research methodologies are effective for industrial applications, using a case study on false call reduction in automated optical inspection to demonstrate that best-practice methods fail and identifying seven weaknesses with experimental consequences.
Are current artificial intelligence (AI) research methodologies ready to create successful, productive, and profitable AI applications? This work presents a case study on an industrial AI use case called false call reduction for automated optical inspection to demonstrate the shortcomings of current best practices. We identify seven weaknesses prevalent in related peer-reviewed work and experimentally show their consequences. We show that the best-practice methodology would fail for this use case. We argue amongst others for the necessity of requirement-aware metrics to ensure achieving business objectives, clear definitions of success criteria, and a thorough analysis of temporal dynamics in experimental datasets. Our work encourages researchers to critically assess their methodologies for more successful applied AI research.