Predicting status of pre- and post-M&A deals using machine learning and deep learning techniques

Risk arbitrage or merger arbitrage is a well-known investment strategy that speculates on the success of M&A deals. Prediction of the deal status in advance is of great importance for risk arbitrageurs. If a deal is mistakenly classified as a completed deal, then enormous cost can be incurred as a result of investing in target company shares. On the contrary, risk arbitrageurs may lose the opportunity of making profit. In this paper, we present an ML- and DL-based methodology for deal announcement prediction based on rumor and takeover success prediction problem. We initially apply various ML techniques for data preprocessing: (a) kNN for data imputation, (b) PCA for lower dimensional representation of numerical variables, (c) MCA for categorical variables, and (d) LSTM Autoencoder for sentiment scores. We experiment with different cost functions, different evaluation metrics, and oversampling techniques to tackle class imbalance in our dataset. We propose four novel classification frameworks that integrate the sentiment scores into the feedforward neural networks in different settings. We optimize the hyperparameter architecture of each model based on the chosen evaluation criteria with SMBO-TPE algorithm. The results show that our model frameworks outperform the benchmark models and also show robust performance over the different market environments.