مطالب

In order to survive in the modern world, organizations must be equipped with the mechanisms that not only maintain their competitive advantage, but also result in their progress and improvement. Prediction of banks’ performances is an important issue, and a poor performance in banks may primarily lead to their bankruptcy, thereby affecting national economics. The bank performance prediction model uses scientific and systematic approaches to diagnose the financial operations of institutes. According to a precise and strict evaluation, the model can detect the weakness of institutions in advance and provide early warning signals to related financial governments. In the present study, we have used three data mining models to predict the future performance of the banks accepted in Tehran Stock Exchange (TSE) and Iran Fara Bourse. Initially, 53 financial ratios were selected and, consequently, reduced to 28 using the fuzzy Delphi technique. The statistical population included 18 banks listed on TSE and Iran Fara Bourse, which   provided their financial statements during the period of 2011 to 2017. Data were collected from the Codal site based on 28 financial ratios using C4.5 decision tree, AdaBoost, and Naïve Bayes algorithm. According to the findings, the Naïve Bayes algorithm was the optimal predictive model with the accuracy of 88.89%.

The stock exchange is considered to be an important establishment to finance long term projects, on one hand, and to collect savings and finance of private section. The stock exchange can be a safe and secure place to invest surplus funds to purchase corporate stocks. As recession and prosperity in this market can have a great role in stockholders` decision-making, it becomes vital to predict these cycles. In this paper, using model MSMH(4)AR(2), we extract the financial cycles of the market. Then, using the ant colony algorithm, we determine the most significant predictors and predict the market financial cycles using neural networks. The results show that the PNN model performs better in predicting the future market with respect to the criteria of mean squared error, the root mean squared error, the model accuracy and kappa coefficient.

Behavioral finance is a new issue raised by some financial intellectuals over the past two decades and has been quickly addressed by professors, experts, and students throughout the world. Investigating the factors affecting investment decisions is carried out in the field of behavioral finance; in other words, the focus of behavioral finance is on the specific charac-teristics of human behavior and applying them in asset pricing. Empirically, pricing models rarely include psychological factors, but the noticeable point is that nowadays, researchers have found behavioral factors influencing empirical asset pricing models that can manipulate returns on asset mispricing. Behavioral asset pricing is the result of applying behavioral finance theories within traditional asset pricing theories. Thus, despite the existence of many asset pricing models, due to their weaknesses and lack of comprehensiveness, as well as the necessity of reviewing behavioral factors, this study aims to model asset pricing through behavioral models. Using the data from 141 listed firms in Tehran Stock Exchange over the years 2008 to 2017 and multivariate regression, this study is an attempts to model asset pric-ing through employing behavioral models and Fama-French approach. Using Fama-French approach, the results showed that accounting information risk, investors’ trading behavior, and investors' sentiment have a direct and significant impact on asset pricing.