Transforming M&A Strategies: The Pioneering Role of NLP
16 April 2024Natural language processing (NLP), a machine learning technology powered by artificial intelligence, can sift through vast quantities of data, highlight specific information and provide deep insights on risks and opportunities of a transaction. The technology is beginning to revolutionize dealmaking.
![Impact_of_NPL_AI-Intralinks](jpg/impact_of_npl_ai-intralinks24bb.jpg?itok=j9Q9wd-c)
In the rapidly evolving world of mergers and acquisitions (M&A), the integration of NLP stands as a beacon of innovation, representing a significant shift in how investment bankers, corporate executives and strategists, and regulators approach these complex transactions. NLP, through its ability to process and analyze vast amounts of unstructured textual data, is unlocking new insights and opportunities in the M&A domain. This blog outlines just some of the groundbreaking research from a number of finance scholars that explore how NLP could be — and indeed is — redefining the M&A landscape.
Predicting M&A participants with NLP
Can NLP predict whether a firm will be acquired or be an acquirer? Based on an NLP analysis of a large set of Form 10-K filings, the answer is “yes.” A study by Carnegie Mellon used the frequencies of words and phrases, showing an improvement in predicting merger targets and acquirers. Further advancing the field, two academics at the University of Münster applied the RoBERTa algorithm, a sophisticated pre-trained transformer neural network capable of handling text cohesively. Their findings showed that textual disclosures in both the business description and the management discussion and analysis sections of Form 10-K filings can significantly enhance predictions of corporate acquisition targets, going beyond traditional financial metrics.
Decoding corporate culture for M&A success
University of British Columbia Finance Professor Kai Li developed a novel machine learning approach with her team to assess corporate culture through the analysis of 209,480 earnings call transcripts, using the Word2Vec algorithm to create a culture dictionary. They score the five corporate cultural values of innovation, integrity, quality, respect and teamwork for businesses. Their research further showed the influence of corporate cultural values on M&A activity, finding that companies valuing innovation and respect are more likely to pursue acquisitions while firms scoring high on the cultural values of integrity and quality are less likely. Moreover, firms with similar cultural values are more inclined to merge, highlighting the role of culture in deal compatibility. This analysis would not have been possible without the NLP model that Professor Li developed.
The Strategic Impact of Language in M&A Deals
A team led by Finance Professor Jarrad Harford at the University of Washington analyzed 5,565 M&A conference call transcripts, employing a probabilistic topic modeling approach to identify 20 key topics related to M&A. Their research revealed that extensive discussions on deal processes are associated with lower completion rates. Topics such as technology, team labor and culture, deal financing and global location significantly influence market reactions to deal announcements, underscoring the strategic importance of communication in navigating M&A transaction complexities.
Unlocking synergies through text analysis
Two academics at the University of Maryland developed a pioneering text-based NLP methodology to assess product market synergies in M&A. Their approach showed that product market language similarity significantly affects merger outcomes, including stock returns and post-merger product expansion, particularly in competitive markets. Together with another academic at the Swiss Finance Institute, they later constructed a further measure of vertical relatedness. They found that R&D-intensive firms are less likely to be acquired vertically, while those with patented innovations are more attractive to vertically related acquirers.
Conclusion: the future of M&A is data-driven
NLP and machine learning transcend their roles as mere tools to become predictive models in the financial domain, transforming extensive unstructured text data into actionable intelligence. The fusion of finance and technology offers new avenues for understanding, predicting and formulating M&A actions such as deal sourcing, deal negotiation and post-merger integration, bringing a new era in which data-driven decisions will predominate.
For more information regarding the application of NLP in M&A transactions, please refer to the complete articles:
Dasgupta, S., Harford, J., Ma, F., Wang, D., & Xie, H. (2020). Mergers Under the Microscope: Analysing Conference Call transcripts. Available at SSRN 3528016.
Frésard, L., Hoberg, G., & Phillips, G. M. (2020). Innovation Activities and Integration Through Vertical Acquisitions. The Review of Financial Studies, 33(7), 2937-2976.
Hoberg, G., & Phillips, G. (2010). Product Market Synergies and Competition in Mergers and Acquisitions: A Text-based Analysis. The Review of Financial Studies, 23(10), 3773-3811.
Li, K., Mai, F., Shen, R., & Yan, X. (2021). Measuring Corporate Culture Using Machine Learning. The Review of Financial Studies, 34(7), 3265-3315.
Lohmeier, N., & Stitz, L. (2023). Identifying M&A Targets from Textual Disclosures: A Transformer Neural Network Approach. Available at SSRN 4373306.
Routledge, B. R., Sacchetto, S., & Smith, N. A. (2013). Predicting Merger Targets and Acquirers From Text. Carnegie Mellon University working paper.
Related Content
![Dr. Siyang Tian Dr. Siyang Tian](jpg/dr.-siyang-tian69be.jpg?itok=vZBP_xwy)
Siyang Tian
Dr. Siyang Tian is a lecturer (assistant professor) in Finance at the University of Sussex and a visiting researcher at Bayes Mergers and Acquisitions Research Centre. He received his Ph.D. in finance from Bayes Business School (formerly Cass). His research interests are in the areas of mergers and acquisitions, corporate governance, fintech and corporate finance, and sustainable finance. His papers have appeared at conferences such as CICF, FMA, and AFA Poster sessions, and in leading journals including the Journal of Banking and Finance.