Augmented Roadmapping: application of data mining and machine learning for sectoral roadmapping processes

• Grant number: 23/04764-7
• Support Opportunities: Regular Research Grants
• Start date: April 01, 2024
• End date: March 31, 2026
• Field of knowledge: Engineering - Production Engineering - Product Engineering
• Principal Investigator: Maicon Gouvea de Oliveira
• Grantee: Maicon Gouvea de Oliveira
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated researchers: Glauco Henrique de Sousa Mendes ; Janaina Mascarenhas Hornos da Costa ; Jonathan Simões Freitas ; Lucas Gabriel Zanon ; Robert Phaal ; Rogério Esteves Salustiano ; Youngjung Geum

Abstract

The digitalisation of roadmapping processes has increased rapidly in the last few years due to advances in information and communication technologies. In particular, data mining and machine learning technologies show great potential to support roadmapping processes, which depend on information to build strategic innovation narratives. In recent years, studies have emerged that aim to understand the application of such technologies to increase the cognitive and decision-making performance of experts involved in roadmapping, i.e., augmenting roadmapping. However, little is known about how to introduce the use of these technologies in roadmapping processes and their potential results. This research project considers two fundamental lines for developing augmented roadmapping processes: databases of strategic information and integrating data mining techniques and machine learning in roadmapping processes. Then, it defines two research questions: What should be the characteristics of strategic information databases for applications with augmented roadmapping processes? How, from these databases, can we use data mining and machine learning techniques in augmented roadmapping processes aimed at industrial innovation? In this context, the main objective of this project is to propose a model of strategic database characteristics for use in roadmapping and how to use them in roadmapping processes supported by data mining and machine learning. The research method for this project is based on design science research (DSR) and case studies. A literature review, interviews with experts, and the development of case studies are proposed for its implementation. As a result, the development of knowledge about the use and impact of data mining and machine learning in industrial augmented roadmapping processes is expected, supporting progress in roadmapping practice and theory. (AU)