Date of Defense
12-2-2024
Date of Graduation
12-2024
Department
Finance and Commercial Law
First Advisor
Zag Davaadorj
Second Advisor
Wenling Lu
Third Advisor
David Mange
Abstract
A comparative analysis is presented between of traditional financial modelling and machine learning (ML) valuation techniques in the context of mergers and acquisitions (M&A). Traditional financial models, such as Discounted Cash Flow (DCF) and comparable company analysis, have long been the standard tools for valuing companies. These methods rely on established financial metrics, are relatively straightforward, and provide reasonably accurate estimates. However, they often fall short on capturing the complexity of market conditions, non-linear relationships, and emerging trends, especially in dynamic sectors or volatile markets. Machine learning, on the other hand, leverages advanced algorithms to process vast datasets, uncover hidden patterns, and adapt to real-time market shifts. By integrating both financial and non0fiancnial data, ML offers higher accuracy, greater adaptability, and the ability to model complex, non-linear relationships between variables. While ML models excel at automating data analysis and reducing human bias, they also present challenges such as data quality issues, interpretability concerns, and the risk of overfitting. The initial setup costs for ML models are higher, and they require substantial investment in technology and expertise. The report identifies several key advantages of ML, including enhanced accuracy, real-time adaptability, and scalability. However, it also highlights the risks, such as dependency on high-quality data and ethical concerns regarding algorithmic bias. In comparison, traditional models, though easier to interpret and less expensive to implement, are less capable of capturing the complexities of modern financial markets.
Recommended Citation
MManga, Rachael, "Enhancing M&A Valuation Accuracy: A Comparative Analysis of Traditional Financial Models and Machine Learning Approaches" (2024). Honors Theses. 3894.
https://scholarworks.wmich.edu/honors_theses/3894
Access Setting
Honors Thesis-Open Access
Financial Data