مطالب

The objective of this study is to present a framework to increase the return and profitability and reduce credit risk of Mellat Bank customers by developing the RFM model. In this study, which was conducted as a case study in Mellat Bank of Iran, first the variables of RFM model were identified. In the next step, relevant weights of RFM variables were calculated using AHP technique. In the next step, using the K-means algorithm, customers were clustered based on weighted RFM and extended RFM. The result included customer clusters. The results indicated that the three clusters 5, 1, and 7 obtained the highest scores for receiving facilities and the coefficients for receiving facilities were equal to 0.271, 0.173, and 0.556, respectively. By determining the facility coefficient for the cluster and consequently for the customers presented in these top groups, granting facility becomes more transparent and more purposeful, and therefore, it will help the company increase profitability, reduce the churn among high-efficiency customers, and create value for customers. This research demonstrates a systematic method for granting facilities to recognize the true value based on the capability and prevention of arbitrary acts

Nowadays, the rapid growth of data in organizations has caused managers to look for a way to analyze them. Extracting useful knowledge from aggregation data can lead to appropriate strategic decision-making for the organization. This paper suggests an application of hybrid network based on amount month demand in every ATM device based on transaction mean of 9 months for 1377 devices to obtain customer behavior patterns, to do so, first designed a basic model based on an auto-regressive with exogenous input network (NARX) then, the optimization of the weight and bias of the designed network is made by the genetic algorithm (GA). As a result, finding the weights of the network represents a nonlinear optimization problem that is solved by the genetic algorithm. Paper results show that the NARX-ANFIS Hybrid network using GA for the learning of rules and to optimize the network weights and weights of the network and the fixed threshold can improve the accuracy of the prediction model. Also, classic models are more efficient and increased benefits and lower financing costs and more rational inventory cash control. As well, the designed model can lead to increase benefits and decrease costs in the bank so that, exact forecast and optimal cash upload in ATMs will lead to increase funds on the bank and rise customers and popularity the brand of the bank.

The increase in non-performing loans considerably reduces profit in the banking systems. To solve these problems, factors influencing the collection of non-performing loans have to be examined in a hopeful attempt to reduce it to an ac-ceptable level. The present study is conducted to analyze and study factors influ-encing the collection of non-performing loans in Shahr Bank. This research is an applied study regarding its goal. It was conducted in two sections, namely the qualitative and quantitative sections. In the qualitative sections, the factors influ-encing the collection of receivables were identified using the theoretical literature and interviews with senior managers of Shahr Bank through the encoding process. In the quantitative section, data was collected by surveying the opinions of 12 experts, including senior managers of Shahr Bank in 2020 using a questionnaire. Thereafter, the factors were selected using the fuzzy Delphi technique and the relationships between them were determined using the fuzzy DEMATEL method. Finally, the factors were weighted and prioritized using the fuzzy ANP method. The research findings showed that non-performing loans can be collected through six types of factors including organizational, regulatory, customer, banking, envi-ronmental, and operational factors. The environmental factor is the most influential factor, while the operational factor is the most influenced and most important factor. In addition, behavioural, contextual, and structural sub-factors have the highest level of importance in the collection of non-performing loans in the order mentioned. These findings can help bank managers make decisions to improve the collection of receivables.

Managing a single portfolio is a basic assumption in the most of research. However, in reality, an advisor manages many accounts at the same time; therefore, there is a significant dependency among portfolios and correlation between decisions on one portfolio with the performance of others, so the results of multi portfolio is different with classic models (single portfolio management, that portfolios are optimized independently) due to market impact and the trade dependency of one account to the other accounts. We propose a structural model to optimize accounts simultaneously, considering interdependences, decision’s correlation and mutual behavioral effects of managed portfolios. Moreover, to compare and analyze both single portfolio and multi portfolio approaches, real data from Tehran Stock Exchange in 1398 are used and model is solved with GAMS. Results indicate that multi portfolio optimization excel other approach and consequence notable improvement on the perspective of customer and advisor. Also, for the validation of the proposed model, the selected stocks are considered in pairs to solve the model and the results show the proper performance of the model with different stocks, thus indicating the validity of the model.

The purpose of this study is to study the indicators for evaluating the effectiveness of the implementation of investment processes on the securities market, taking into account the scientific foundations of information management systems and analysis of indicators of financial efficiency of the investment function of the securities market in Ukraine. The relevance of this study is due to the growing importance of management information systems in all sectors of the Ukrainian economy, in particular, the provision of solutions to the problems of activating investment processes in the securities market of Ukraine by analyzing and reassessing the effectiveness of investment processes at this level, taking into account the scientific basis of management information systems.  A set of indicators that best reflect the implementation of the investment function of the Ukrainian securities market is proposed. A matrix of characteristics of investment processes in the securities market is proposed. It is argued why domestic and foreign investors prefer local securities market indices when making investment decisions. Through the implementation of correlation-regression models, it has been proven that, on average, 87% of changes in investments in securities are due to changes in the number of licensed entities, which on the Chedoch scale indicates a close relationship between the indicators. The results obtained using statistical inference methods indicate a high impact of both external macroeconomic factors that inhibit the development of the securities market and internal, which in turn is reflected in the indicators of assessing the effectiveness of investment processes in the securities market.

An administrator is employed to identify network security breaches in their organizations by using a Network Intrusion Detection and Prevention System (NIDPS), which is presented in this paper that can detect and preventing a wide range of well-known network attacks. It is now more important than ever to recognize different cyber-attacks and network abnormalities that build an effective intrusion detection system plays a crucial role in today's security. NSL-KDD benchmark data set is extensively used in literature, although it was created over a decade ago and will not reflect current network traffic and low-footprint attacks. Canadian Institute of Cyber security introduced a new data set, the CICIDS2017 network data set, which solved the NSL-KDD problem. With our approach, we can apply a variety of machine learning techniques like linear regression, Random Forest and ID3. The efficient IDPS is indeed implemented and tested in a network environment utilizing several machine learning methods. A model that simulates an IDS-IPS system by predicting whether a stream of network data is malicious or benign is our objective. An Enhanced ID3 is proposed in this study to identify abnormalities in network activity and classify them. For benchmark purposes, we also develop an auto encoder network, PCA, and K-Means Clustering. On CICIDS2017, a standard dataset for network intrusion, we apply Self-Taught Learning (STL), which is a deep learning approach. To compare, we looked at things like memory, Recall, Accuracy, and Precision.

On a global scale, one of the prevalent causes of dementia is Alzheimer’s disease (AD). It will cause a steady deterioration in the individual from the mild stage to the severe stage, and thus impair their capacity to finish any tasks with no aid. The diagnosis is done with the utilization of existing methods which include medical history; neuropsychological testing as well as MRI (Magnetic Resonance Imaging), a lack of sensitivity as well as precision does affect the consistency of efficient procedures. With the deep learning network’s utilization, it is possible to create a framework for detecting specific AD characteristics from the MRI images. While automatic diagnosis is done with the application of diverse machine learning techniques, the existing ones do suffer from certain constraints with regards to accuracy. Thus, this work’s key goal is to increase the classification’s accuracy through the inclusion of a pre-processing approach prior to the deep learning model. The Alzheimer's disease Neuroimaging Initiative (ADNI) database of AD patients was used to develop a deep learning approach for AD identification. In addition, this study will present ideas for Haralick features, feature extraction from Local Binary Pattern (LBP), Artificial Neural Network (ANN), and Visual Geometry Group (VGG)-19 network techniques. The results of the experiments show that the deep learners offered are more effective than other systems already in use.

Understanding how discourse is spatialized needs a conceptual ground for the discussion, and this study believes that the Foucauldian view is the right one. With a non-cartesian attitude, Michel Foucault considered the body as space and used archaeological and genealogical analysis to study its productive conditions. In his archaeological study, Foucault sought to analyze changes in knowledge or discourse through historical periods. In the genealogical one, he revealed discourse emergence conditions via mechanisms of power. Taking Foucault's epistemic framework, power and knowledge have a mutual relationship, and spaces represent power/knowledge. This paper explores spatial discourses in Naghsh-e-Jahan Square of Isfahan (1591-1941 A.D.) as the last public-government square from the Safavid era. Ultimately, the spatial discourses of the Naghsh-e-Jahan square can be traced by techniques of domination in different periods of history; the discourse of Islamization through sovereign power in the Safavid era, the discourse of modernization through disciplinary power in the Ghajar era, and the modernization, civilization, and nationalism through disciplinary power and biopower in the late Ghajar era and during the first Pahlavi era.

The portfolio selection problem is one of the main investment management prob-lems. In the portfolio selection problem, robustness is sought against uncertainty or variability in the value of the parameters of the problem. This paper has been conducted for Robust portfolio optimization based on the mean-cvar approach. And introduces the linear mean-cvar model as a criterion for calculating risk and provides an optimal Robust mean-cvar model. Robust approach used in this research is the Bertsimas and Sim. In this approach, Robust counterpart presented for a linear programming model remains linear, maintaining the advantages of the linear programming model in the optimal model. The model developed in this research is randomly selected by real data of 20 stocks of the S&P 500 index for three years, this development help portfolio selection problem to consider uncertainty. Interval optimization is modeling approach to consider parameters uncertainty in this paper. Considering uncertainty make model more realistic. The results of model show that this approach has computational efficiency and on the other hand proposed model produce better solution in risk and portfolio rate of return point of view