Human-Centered AI Product Prototyping with No-Code AutoML: Conceptual Framework, Potentials and Limitations
It addresses the problem of limited accessibility to AI prototyping tools for non-experts, presenting an incremental framework.
This paper tackles the challenges of AI product prototyping for non-experts by proposing a conceptual framework that integrates no-code AutoML to improve accessibility and interpretability, validated through a hybrid evaluation method showing efficacy in supporting non-experts and streamlining decision-making.
This paper addresses the complexities inherent in AI product prototyping, focusing on the challenges posed by the probabilistic nature of AI behavior and the limited accessibility of prototyping tools to non-experts. A Design Science Research (DSR) approach is presented which culminates in a conceptual framework aimed at improving the AI prototyping process. Through a comprehensive literature review, key challenges were identified and no-code AutoML was analyzed as a solution. The framework describes the seamless incorporation of non-expert input and evaluation during prototyping, leveraging the potential of no-code AutoML to enhance accessibility and interpretability. A hybrid approach of combining naturalistic (case study) and artificial evaluation methods (criteria-based analysis) validated the utility of our approach, highlighting its efficacy in supporting AI non-experts and streamlining decision-making and its limitations. Implications for academia and industry, emphasizing the strategic integration of no-code AutoML to enhance AI product development processes, mitigate risks, and foster innovation, are discussed.