Using a large and unique patent‐merger data set over the period 1984 to 2006, we show that companies with large patent portfolios and low R&D expenses are acquirers, while companies with high R&D expenses and slow growth in patent output are targets. Further, technological overlap between firm pairs has a positive effect on transaction incidence, and this effect is reduced for firm pairs that overlap in product markets. We also show that acquirers with prior technological linkage to their target firms produce more patents afterwards. We conclude that synergies obtained from combining innovation capabilities are important drivers of acquisitions. This article is protected by copyright. All rights reserved.