Mergers e Acquisitions represent important forms of business deals because of the volumes involved in the transactions and the role of the innovation activity of companies. By considering the patent activity of about one thousand companies, we develop a method to predict future acquisitions by assuming that companies deal more frequently with technologically related ones. We address both the problem of predicting a pair of companies for a future deal and that of finding a target company given an acquirer. We compare different forecasting techniques, including machine learning and network-based algorithms, showing that our measure of similarity between companies outperforms the other approaches. Finally, we present the Continuous Company Space, a two-dimensional representation of firms to visualize their technological proximity and possible deals. Companies and policymakers can use this approach to identify companies most likely to pursue deals or explore possible innovation strategies.
Using our technology, companies can find the best partners for a deal (merger, acquisition, etc.). This recommendation stems from the construction of a space of companies, whose relative distance is computed using network science and machine learning. In this space, two companies are "close" from a technological point of view, so if the two have similar patenting activities. However, a target firm could be recommended to an acquiring company because of its distance, if the acquirer is looking for a complementary patenting activity, or wants to enter a new market.