The modelling fixed asset investment With the role of regulatory criteria and artificial intelligence approach
Subject Areas : Financial Engineering
Farzaneh SHamsdoost
1
(PhD student in financial engineering, Department of Management, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran)
Omid Mahmoudi khoshroo
2
(Faculty Member, Accounting Department, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran)
Ataollah Mohammadi Malgharni
3
(Faculty Member, Accounting Department, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran)
Amir SHeikhahmadi
4
(Faculty member, Department of Computer Engineering, Sanandaj branch of Islamic Azad University, Sanandaj,)
Keywords: Fixed asset invetment, Regulatory criteria, Artificial Intelligence, Linear and non-linear models.,
Abstract :
The purpose of this research is to model fixed asset investment with the role of regulatory criteria and artificial intelligence approach of companies admitted to the Tehran Stock Exchange. The variables of the companies are selected based on the RRelief-F method. Then the data is divided into K-fold validation, and the data is divided into test and training data by cross-validation. Then the training data is calculated with four linear and non-linear artificial intelligence algorithms PINSVR and linear and non-linear pls. In the training phase of linear and non-linear models after learning, the same training-validation data without the dependent variable is provided to them again to determine the value of the fixed asset prediction variable.The statistical population of the current research is all the companies admitted to the Tehran Stock Exchange in the period from 2012 to 2021, and the financial information of 101 companies was used. The results of the research hypothesis test showed that in terms of regulatory criteria, the size of the board of directors, the independence of the board of directors, the financial expertise of the board of directors, the size of the audit committee, the independence of the audit committee, institutional ownership above 5%, the tenure of the CEO, the existence of an internal auditor, the ratio of expertise Committee members and CEO duality play an important role in predicting firms' fixed investment. Also, linear artificial intelligence algorithms are more efficient in predicting investment in fixed asset of companies than non-linear algorithms.