Abstract
For decades, a high prediction error rate of firm value assessment has been reported by using traditional financial evaluation methods, therefore develop a suitable assessment tool to improve firm value prediction accuracy is in urgent. This paper provides a comprehensive review and statistical comparison of six machine learning models: K-Nearest Neighbor, Decision Trees, Support Vector Regression, Artificial Neutral Network, AdaBoost, and Random Forest in oil firm and power firm value prediction. Based on nearly 5000 M&A items, this paper finds that for both oil and power industries, the prediction error of ANN is the lowest in all the three measurement terms. ANN performs better than the other five ML models by 18% at least for oil industry, and outperforms the others by 19% for power industry. It shows that ANN models can produce both accurate and reasonably understandable prediction results. ANN can be applied to a wide range of M&A decisions and value assessment for energy firms.
Highlights
Mergers and acquisitions (M&A) is the combination of the assets and liabilities of two companies to form a new business entity
This paper compares the prediction performance of four supervised learning models, namely K-Nearest Neighbor (KNN), Decision Trees (DT), Support Vector Regression (SVR), Artificial Neural Networks (ANN), and two ensemble models-AdaBoost (AB), Random Forest (RF), and the results show that the ANN could predict both oil and power firm values more accurately than its competitors on all error terms stably
The lowest prediction error is achieved by ANN at 8.64, 19% lower than other models
Summary
Mergers and acquisitions (M&A) is the combination of the assets and liabilities of two companies to form a new business entity. Determining the value of target companies is not easy. Even with rigorous logical reasoning and statistical regression, decision maker can hardly make reliable predictions. There are two methodologies in predicting firm price: (1) traditional linear regression methods, and (2) machine learning approach. This paper provides a comprehensive literature review of the six ML models-KNN, DT, SVR, ANN, AB and RF, as well as their application in firm value assessment. A. K-NEAREST NEIGHBOR REGRESSOR MODEL KNN is a simple, effective non-parameters method. K-NEAREST NEIGHBOR REGRESSOR MODEL KNN is a simple, effective non-parameters method It calculates the similarity between a target object and the most similar k-nearest neighbors in the training sample set by Euclidean distance, n d(x, xi) = (x − xi) (1).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
