When to use machine learning? And which problems stand to benefit?

Abstract Despite the continued success of machine learning (ML), its indiscriminate use may not always yield the expected benefits, can waste resources, introduce unforeseen complexities, and even lead to failure. From this lens, this paper systematically addresses the following elemental questions: When should we integrate ML, and which problem-solving workflows benefit the most? Thus, this paper critically examines existing decision making frameworks and guidelines to identify their strengths and limitations in defining ML applicability. Then, through a comprehensive literature review and analysis, we outline explicit suitability criteria to assess when ML should be favored over traditional engineering methods. Based on this analysis, we propose a conceptual structured decision making framework that incorporates practical steps and checklists to guide engineers in method selection, model development, validation, and deployment. Additionally, this paper highlights critical challenges and potential future research questions.