Segmentation of Construction Companies Based on Financial Performance Indicators for Acquisition Using K-Means

Abstract

The acquisition process in the construction industry requires careful evaluation of potential targets, particularly regarding financial performance. Data-driven segmentation has become a strategic method to group companies based on financial characteristics, enabling objective acquisition decisions. This study applies the K-Means Clustering algorithm to segment construction companies using key financial indicators, including P/E ratio, Price-to-Book Value (Price to BV), D/E ratio, ROA, ROE, and NPM. Secondary data from financial statements of construction companies listed on the Indonesia Stock Exchange (IDX) during 2023–2024 were analyzed. Five clusters were identified, reflecting varying levels of financial performance and risk. Among the 23 companies studied, 18 experienced a decline in performance. Notably, PT Totalindo Eka Persada Tbk showed the most significant decline, with a high D/E ratio and negative NPM, suggesting it as a potential acquisition target at a lower price. Post-acquisition, financial and operational restructuring, governance improvements, project diversification, and cost-efficiency measures are recommended. Each cluster presents distinct characteristics relevant for acquisition strategy; for example, high-profitability but low-solvency clusters may attract high-risk investors. This study demonstrates how data mining techniques support corporate due diligence and strategic decision-making, offering a structured approach to identify companies with differing financial strengths and weaknesses. The findings contribute to advancing quantitative approaches in acquisition planning, highlighting how clustering techniques can enhance objective evaluation and strategic alignment in mergers and acquisitions.