Predicting M&A Targets Using Machine Learning Techniques
The full article can be found on LSEG’s Developer Portal. It was written by Haykaz Aramyan.
How we can predict Mergers and Acquisitions (M&A) targets using Machine Learning (ML) and discover if that will produce an abnormal return for investors? With ML libraries, and the London Stock(LSEG)’s Refinitiv Data Platform (RDP) REST API of course!
The overview of the Article
In this article, we built a predictive model for Mergers and Acquisitions (M&A) target identification and discover if that will produce an abnormal return for investors. We have trained a Logistic regression model which was based on financial variables describing the profitability, leverage, and liquidity aspects of the company. Additionally, we have introduced a clustering approach based on the KMeans Algorithm to improve the prediction output and investment returns of the model.
To prove the conversion of the prediction accuracy into an investment return, we have constructed minimum misclassification and maximum concentration portfolios and tracked investment returns from multiple investment strategies.
The Article is utilizing the depth and width of Refinitiv data and APIs, particularly Refinitiv’s EIKON Data API to access the M&A, financial, and the peers' data.
The conclusion of the Article
Overall, the article’s findings indicate that it is possible to predict target companies, and clustering can improve the prediction power of the models. Clustering the sample dataset through the Kmeans algorithm resulted in grouping higher liquid and lower levered companies in one cluster and the opposite in another. Clustered models produced better accuracy and explanatory power than the general model.
Although the findings indicate that it is possible to predict target companies, and clustering can improve the prediction power of the models, higher predictive power did not always converge into higher returns due to the difference in the size of the actual returns of classified companies. This is making the abnormal return generation by identifying target companies extremely challenging. Nevertheless, the predictive model based on the higher liquid, lower levered cluster produced the market excess returns in almost all scenarios during the examined period.
References
Downloads
Related Articles
- Predicting M&A Targets Using ML: Unlocking the potential of NLP based variables — January 10, 2022, Haykaz Aramyan
- Create Technical Analysis triggers and signals using the Eikon Data API, March 10, 2020, Umer Nalla
- Portfolio optimization in Modern Portfolio Theory, November 29, 2019, Alex Putkov
- Information Demand and Stock Return Predictability (Coded in R), January 05, 2021, Jonathan Legrand
- Explore all Articles
