machine learning algorithm

The main aim of the represented research is to provide a comprehensive model for predicting the type of audit opinion based on a number of machine learning algorithms in some companies in the Tehran Stock Exchange. In order to achieve this goal, 1,606 company-years (146 companies for 11 years) observations collected from the annual financial reports of companies admitted to the Tehran Stock Exchange from 2010 to 2020 have been tested. In this study, six machine learning algorithms (decision tree and regression, random forest, neural network, nearest neighbor, logit regression, support vector machine) and also two methods of selecting the final variables of the research (two samples mean comparing test, forward step-by-step selection method) has been used for the model creation. The results show that the overall accuracy of decision tree and regression, random forest, neural network, nearest neighbor, logit regression, and support vector machine procedures respectively are 78.7%, 77.7%, 76.9%, 74.6%, 78.3%, and 76.7%. Regarding the obtained outcomes, the decision tree and regression algorithm outperform in forecasting the type of audit opinion compared to other studied methods. Meanwhile, in general, the result of variable selection techniques illustrates that the step-by-step method is far more effective. Hence, in the studied companies in the Tehran Stock Exchange, the step-by-step method and the decision tree and regression algorithm provide the most efficient model for the prediction of the audit opinion type.

Artificial intelligence plays an important role in the field of personal computers. Right now personal computers are part of our lives, so AI should be used in all everyday tasks. Humans are great thinkers, but machines can be more effective at counting than humans. The machine cannot fully explain different conditions, but it can create a different type of connection between different salient points and features. Either way, there can be many benefits to establishing machine learning computing in our daily lives. Machine learning or machine learning is one of the subsets of artificial intelligence that enables systems to learn and improve automatically without explicit programming, and controlling the credit risk of real bank customers is one of these benefits that can help the monetary and banking system to improve conditions and reduce risk. Therefore, the use of machine learning to create an algorithm to manage credit risks is a topic addressed in this research.

ABZU is an explainable non- linear model, that has reimagined artificial intelligence to completely change the way problems are solved. It has a new standard of interpretability that has simple visual depictions and mathematical expression for models developed which yields high accuracy. From this, a model developed can be highly accurate and algorithm is recognized to all. This makes more complicated predictions in an easier level and explore new features of the model. This can be achieved through leveraging the results in the form of graphs and representing it. This algorithm applied in the fields of Artificial Intelligence / Machine Learning will yield an accurate result. This improves efficiency and increases the model’s reusability.