Presenting the Model of the Effect of the Degree of Group Similarity on the Quality of Accounting Information and the Quality of Financial Reporting on the Valuation of the Initial Public Offering of Shares Using the Algorithm of Artificial Neural Networks

Objective. The pricing and valuation of initial public offerings (IPOs) are the subject of extensive literature in finance, primarily focusing on well-documented pricing anomalies such as IPO underpricing and significantly abnormal post-issuance returns. The use of peer company information to value IPOs has received attention due to their signaling role. Among the things that can be compared in the field of peer companies is the quality of their accounting information and financial reporting. Due to the lack of accounting information related to IPOs, practitioners rely significantly on comparable Peer Accounting Information when attempting IPO Valuation. Firms desiring to obtain capital through an IPO depend on more accounting information than their own when transitioning from a relatively opaque to a relatively transparent information environment, such as the accounting information of their priced peers. According to these cases, this research aims to present the model of the effect of the degree of group similarity, the quality of accounting information and the quality of financial reporting on the valuation of the initial public offering of shares using the algorithm of artificial neural networks.
Method: This research is practical in terms of purpose and data collection method; it is ex-post facto research in accounting proof research. The statistical population of this research includes 92 companies listed on the Tehran Stock Exchange between 2012 and 2020, which uses the multiple regression method to test the hypotheses. The degree of similarity of the quality of accounting information of the supplier company with the peer group has been calculated and tested separately using three indicators of abnormal accruals, profit predictability and profit stability. Also, considering that artificial network patterns can be used to predict the valuation of an initial public offering of stocks and probably have different powers, this research compares the power of three algorithms (firefly algorithm, machine regression algorithm, decision, and tree algorithm).
Results: The comparable companies' approach to pricing IPOs depends largely on the availability of accounting information from peer companies already priced in the market. However, to be most effective, peer accounting information should be useful in making decisions about how to use the accounting information of peer companies. The results showed that the valuation of shares in an initial public offering is possible based on the degree of similarity of the companies in the group and the quality of the accounting information. Stock valuation in initial public offerings based on profit and sales approaches differs in terms of the similarity of group companies and the quality of the company's accounting information. Group companies and the quality of accounting information aren’t associated with incorrect pricing (overvaluation and undervaluation) in initial public offerings. The results of neural networks also indicated that the firefly algorithm has a higher power to predict the initial public offering valuation than the machine regression algorithm; the firefly algorithm had a higher power to predict the initial public offering valuation than the tree algorithm. The decision tree algorithm is more likely to predict the valuation of the initial public offering of stocks than the support vector machine regression algorithm.
Conclusion: in the comparison between valuation theory and practice (use of information of peer companies), the second view is more effective, and the accuracy of information of peer companies is a key component of pre-publication estimates of the accuracy of information of IPO companies, and the information set of an IPO, it is not limited to its own accounting information, but also includes the information of its peers. Given that companies often decide to offer their initial shares when they think they can maximize their equity earnings (such as when they feel their stock is overvalued or during periods of booming stock markets and heightened investor sentiment), the results of this research can be used by potential investors to reduce the effect of underwriters' incorrect valuation and to monitor them, especially in the emotional stock market; Therefore, it is suggested that buyers of shares of companies that are listed on the stock market for the first time should consider the accounting information and quality of financial reporting of similar and peer companies, especially the quality of accruals and the predictability and stability of their profits; because it contains information about the future price estimation of initial supply companies. Underwriters and initial price estimators are also suggested to consider the quality of accounting and financial reporting of their peers in estimating the initial price of initial public offering companies. In the end, due to the higher power of the Firefly algorithm to predict the valuation of the initial public offering of stocks compared to the vector machine regression algorithm and the decision tree, it is suggested to use these algorithms for valuation due to the lower error.