Development of data-driven technology roadmap considering dependency: An ARM-based technology roadmapping

The active incorporation of business data has become a vital process in the recent business environment. Despite the potential utility of massive database, technology roadmap, a well-known strategic planning method, still remains a subjective and qualitative method conducted by some experts. Even if some studies have tried, previous research lacks a dependency measure that can be used between layers, which is a critical part of technology roadmaps. This paper therefore suggests an association rule mining (ARM)-based technology roadmap to identify the relationship between different layers. The use of ARM fits the purpose, in terms of capturing the dependency information. Two types of roadmap are developed: a keyword portfolio map and a keyword relational map. In the keyword portfolio map, four types of keyword pairs are identified according to their support and confidence. In the keyword relational map, a 2-dimensional map is developed using support as an intra-layer affinity relationship and confidence as an inter-layer dependency relationship.