Lee, Myunghwan, Gene Moo Lee, Hasan Cavusoglu, Marc-David L. Seidel. “Strategic Competitive Positioning: An Unstructured Structural Hole-based Firm-specific Measure”, Under Review. [Submitted: Dec 7, 2022]

• doc2vec model of 10-K reports: Link
• Presented at UBC MIS Seminar 2018, CIST 2019 (Seattle, WA), KrAIS 2019 (Munich, Germany), DS 2021 (online), KrAIS 2021 (Austin, TX), UT Dallas 2022, KAIST 2022, Korea Univ 2022, INFORMS 2022 (Indianapolis, IN)
• Funded by Sauder Exploratory Grant 2019
• Research assistants: Raymond Situ, Sahil Jain

In this paper, we propose a firm-specific strategic competitive positioning (SCP) measure to capture a firm’s unique competitive and strategic positioning based on annual corporate filings. Using an unsupervised machine learning approach, we use structural holes, a concept in network theory, to develop and operationalize an SCP measure derived from a strategic similarity matrix of all existing U.S. publicly traded firms. This enables us to construct a robust firm-level SCP measure with minimal human expert intervention. Our measure dynamically captures competitive positioning across different firms and years without using artificially bounded and often outdated industry classification systems. We demonstrate the effectiveness of our measure with an empirical analysis showing the imprinting effect of SCP at the time of the initial public offering (IPO) on the subsequent performance of the firm. The results show that our unsupervised SCP measure predicts post-IPO performance. This paper makes significant contributions to the information systems and strategic management literatures by proposing a network theory-based unsupervised approach to dynamically measure firm-level strategic competitive positioning. The measure can be easily applied to firm-specific, industry-level, and cross-industry research questions across many fields and contexts.