Forecasting the Price of the Candidate in M&A Based on Multiple-Kernel SVMR

In Mergers and Acquisitions, forecasting the price of the candidate is a very important step, which decides whether an acquisition continues to advance. In this paper, multiple-kernel SVMR is applied to predict the price of candidates in mergers and acquisitions. In the model, we adopt a two-stage multiple-kernel learning algorithm by incorporating sequential minimal optimization and the gradient projection method. By this algorithm, advantages from different hyperparameter settings can be combined and overall system performance can be improved. Experimental results show that SVMR performs better than other methods which a strong tool for M&A decision-making.