درخت حوزه‌های تخصصی

One of the most important risks that the banks and financial institutes face, is credit risk which is related to not-paid instalments or the instalments paid with delay by borrowers. Banks use credit scoring models In order to prevent this type of risk. The goal of this research is to investigate the joint effect of economic time cycles and the industry sector on credit scoring models we are seeking to answer the key question: “when should bank change their credit scoring models based on economic time cycles and for which industry sectors?”. The dataset of the research involves all companies that were applied for a loan in one of the Iranian major banks during the years 2008-2011. The companies have been divided into four industry sectors including “Industry and Mine”, “Oil and chemical”, “Service and Infrastructure” and finally “Agriculture”. Based on the sector of the industry and year, 54 explanatory variables, both financial and non-financial, 12 distinct industry sectors and time-specific data sets are built then classification methods were used to classify customers into two groups of defaults and non-defaults. Finally, we compared the results by Wilcoxon Test. The results show that the companies that are in the groups of Industry and Mine and Agriculture, need their own special credit scoring based on industry type model and time but two other groups don’t need of course in the studies dataset duration. Finally, the study concluded by introducing the credit scoring strategies for different four-cycle of economies

SCImago Journal Rank (SJR) is one indicator of a journal's reputation.  The value is calculated based on several published journals, such as scholarly journals' scientific impact, representing the number of quotes sent to a journal and the relevance or reputation of journals from which the quotations originate. A high SJR value means that the corresponding journal has a high reputation. This study aims to approach the SJR classification by implementing a machine learning approach. A simple yet powerful method Naïve Bayes Classifier (NBC), is selected. NBC utilizes probability calculations based on Bayes' theorem. However, NBC has an assumption that the attribute values do not depend on each other. This method is optimized using Particle Swarm Optimization (PSO) to overcome this weakness. This study used SJR data of the computer science domain from 2014 to 2017. Publication without Q rank is filtered for better performance. As a result, the accuracy of the proposed method is higher than the baseline. The use of PSO  significantly improves the NBC performance based on the performed T-test. The PSO-NBC selects four of eight features: H index, Cites/ Doc (2 Years), and Ref. / Doc. Overall results show that using PSO-NBC is closer to SJR rather than using mere NBC.