The optimized model of factors effecting on the Merger and Acquisition from multiple dimensions with neural network approach.

Document Type : Original Manuscript


1 Ph.D. Student of Financial Engineering, Babol Branch, Islamic Azad University, Banol, Iran

2 Ph.D. Associated Professor, Department of Management, Babol Branch, Islamic Azad University, Banol, Iran

3 Ph.D. Assistant Professor, Department of Economey, Babol Branch, Islamic Azad University, Banol, Iran


Nowadays, firms apply the merger and acquisition strategy for gaining synergy, increasing the wealth of stockholders, economics of scales, enhancing efficiency, increasing the ability to research and develop, developing the firm and decreasing the risk. Developing an optimized model with the ability to identify the effective variables on the merger and acquisition process has a significant role on predicting the profit and the risk of companies involved in this process. Recently, regression-based approaches have been used for providing the optimized model. Regression method has some challenges such as sensitivity to considering the inner data structure, inability to addressing the non-linear relations between data, improper handling of data with continuous value. Neural network has the ability to more precise analysis of the relation between data due to lack of the challenges with regression method as well as examining both internal and external data structure. In one hand, since regression methods are the simplest type of neural method or neural method without hidden layer, developing regression method into neural network and concentrating on neural network and improving these networks can play more effective role on applying prediction in comparison with regression or other ordinary neural networks. Hence, this paper suggests using the optimized neural network for providing an optimized model in order to measuring the effective factors on the merger and acquisition process from multiple dimensions. The results from the experiments indicate the appropriateness of the optimal neural network-based model.


Main Subjects