"The Flow in the Funnel": Modeling Organizational and Individual Decision-Making for Designing Financial AI-Based Systems

From service design thinking to the third generation of activity theory: a new model for designing AI-based decision-support systems

Introduction

The rise of Artificial Intelligence (AI), particularly machine learning, has brought a significant transformation in decision-making (DM) processes within organizations, with AI gradually assuming responsibilities that were traditionally performed by humans. However, as shown by recent findings, the acceptance of AI-based solutions in DM remains a concern as individuals still strongly prefer human intervention. This resistance can be attributed to psychological factors and other trust-related issues. To address these challenges, recent studies show that practical guidelines for user-centered design of AI are needed to promote justified trust in AI-based systems.

Methods and results

To this aim, our study bridges Service Design Thinking and the third generation of Activity Theory to create a model which serves as a set of practical guidelines for the user centered design of Multi-Actor AI-based DSS. This model is created through the qualitative study of human activity as a unit of analysis. Nevertheless, it holds the potential for further enhancement through the application of quantitative methods to explore its diverse dimensions more extensively. As an illustrative example, we used a case study in the field of human capital investments, with a particular focus on organizational development, which involves managers, professionals, coaches and other significant actors. As a result, the qualitative methodology employed in our study can be characterized as a "pre-quantitative" investigation.

Discussion

This framework aims at locating the contribution of AI in complex human activity and identifying the potential role of quantitative data in it.

Enhancing organizational processes for service innovation: strategic organizational counseling and organizational network analysis

Previous studies have primarily focused on product innovation, overlooking the examination of organizational processes. This limited perspective poses a theoretical and practical gap as it primarily considers the external aspects of innovation. On the contrary, organizational processes play a crucial role in improving and creating internal operations necessary for product/service innovation success. To this aim, this paper presents a novel approach to enhancing service innovation within complex organizations by integrating Strategic Organizational Counseling (SOC) and Organizational Network Analysis (ONA) methodologies. More specifically, SOC supports organizations in understanding and defining the professional families that need to be triggered in the service ideation, delivery and commercialization process, especially in the case of complex organizations with multiple departments. Secondly, ONA enables the identification of the intra-organizational nodes within the professional families that, due to their social position and other personal characteristics, can be actively engaged as Ambassadors for the promotion of innovation practices. By focusing on intra-organizational processes, understanding role-related needs, and selecting influential organizational actors, this approach provides a new perspective on the service innovation process, assuming both a micro and macro viewpoint. The paper also highlights the importance of cyclically monitoring the proposed workflow to adapt to the dynamic nature of innovation.

Detecting fake news and disinformation using artificial intelligence and machine learning to avoid supply chain disruptions

Fake news and disinformation (FNaD) are increasingly being circulated through various online and social networking platforms, causing widespread disruptions and influencing decision-making perceptions. Despite the growing importance of detecting fake news in politics, relatively limited research efforts have been made to develop artificial intelligence (AI) and machine learning (ML) oriented FNaD detection models suited to minimize supply chain disruptions (SCDs). Using a combination of AI and ML, and case studies based on data collected from Indonesia, Malaysia, and Pakistan, we developed a FNaD detection model aimed at preventing SCDs. This model based on multiple data sources has shown evidence of its effectiveness in managerial decision-making. Our study further contributes to the supply chain and AI-ML literature, provides practical insights, and points to future research directions.

The contribution of activity theory to modeling multi-actor decision-making: A focus on human capital investments

Making investment decisions is usually considered a challenging task for investors because it is a process based on risky, complex, and consequential choices (Shanmuganathan, 2020). When it comes to Investments in human capital (IHC), such as startups fundings, the aspect of decision-making (DM) becomes even more critical since the outcome of the DM process is not completely predictable. Indeed, it has to take into consideration the will, goals, and motivations of each human actor involved: those who invest as well as those who seek investments. We define this specific DM process as multi-actor DM (MADM) since not a group is making decisions but different actors, or groups of different actors, who – starting from non-coinciding objectives – need to reach a mutual agreement and converge toward a common goal for the success of the investment. This review aims to give insights on psychological contributions to the study of complex DM processes that deal with IHC to provide scholars and practitioners with a theoretical framework and a tool for describing the complex socio-ecological systems involved in the DM processes. For this purpose, we discuss in the paper how the third generation of activity theory (Leont’ev, 1974, 1978;Engeström, 1987, 2001) could be used as an appropriate model to explain the specificities of MADM construct, focusing on the particular case of startup funding. Design thinking techniques will be proposed as a methodology to create a bridge between different activity systems.