clustering

In order to invest properly and identify the right short and long positions, the existence of an efficient strategy is necessary. Pairs trading system is one of the most famous algorithmic trading systems. In this system, a pair of stocks that have same trend in the long-time (reversion to the mean) and have fluctuations (spread) in the short-time is used. The most important point is to identify such a pair of stock. In this research, an approach is used to identify pairs of stocks and also to find the right short and long positions in trading pairs. In the first step, a stock pair that has a long-time statistical relationship is selected. The DTW method is used to calculate the distance between each stock pair and their movement similarity. Then, the hierarchical clustering method is used to cluster stocks, and then pairs of stocks that have a greater degree of similarity are selected. In the second step, the SVM method is used to identify buying and selling positions. In order to check the performance of the method, the S&P 500 index, which includes the top 500 stocks of the New York Stock Exchange, has been used.

Enhanced index Tracker portfolio, as one of the investment management strategies, is trying to combine the benefits of both active and passive approaches. This research is going to provide a two-stage model that can first reproduce the index performance with a smaller number of index-forming shares and, secondly, calculate the Enhanced index tracker portfolio weights.

In the first step, using a binary mathematical programming model to create clustering of time series, an index tracker portfolio was created. Coppola-based correlation coefficients and mutual information were used as time series similarity measures at this stage. In the second stage, the weight of investment in the selected shares was determined in a way that the return on the portfolio surplus was maximized relative to the index created in the first stage. The uncertainty resulting from the estimation of the excess stock returns in the second phase was considered by using a robust optimization approach.

The results obtained by applying the out of sample test on the 50 more active companies in the Tehran Stock Exchange from the spring of the Iranian calendar year of 1394 to spring of 139, using the tracking error and market ratio, indicate that in addition to the success of the similarity criteria in time series clustering and index tracking, at a confidence level of 99%; Enhanced index Tracker portfolios based on normal, T and Clayton Copula correlation coefficients have a positive significant difference with the index.

According to this study, to develop an enhanced index tracker portfolio, it is practical to apply copula-based correlation coefficients and try a robust optimization approach to take into account the uncertainty of the parameters.

The purpose of this study is to create a Financial network to identify stock market leaders using centrality measures.This study finally provides a clustering of superior stocks that can be used as an optimal stock portfolio by investors.The statistical population of all stock exchanges is that the 100 companies with the most capital were selected as a statistical sample over a period of 11 years.Due to the nature of the research ranking, the Kendall correlation coefficient was used to calculate the correlation.The Prime algorithm was used to identify relationships and construct the minimum spanning tree, and the fast-greedy algorithm was used to cluster stocks.The results show that in terms of degree centrality measure, stocks of Sepahan Cement companies,Omid Investment Management and Bank Melli Investment, based on closeness centrality measure, stocks of Sepahan Cement companies,International Building Development, and Khuzestan Steel, based on Betweenness centrality measure, the stocks of Sepahan Cement, Ghadir Investment and Bank Melli Investments, and finally based on the bottleneck centrality measure,the shares of Sepahan Cement, Khuzestan Steel and International Building Development have the greatest impact on the stock exchange network. Also, the top stocks were classified into 11 clusters,each of which shows a strong relationship between its components.

The need to achieve optimal portfolio optimization criteria, which, in addition to the accuracy of investment decisions quickly, goes beyond academic needs, as investors, investment companies and investment managers need to reduce their investment losses, increase Risk-adjusted returns have always been discussed. However, it is very difficult to achieve a portfolio optimization method that fills the gap between applied requirements and theoretical models. Considering that one of the most important factors in achieving optimal returns is diversification. This research, with the theme of "Formation of optimal investment portfolio in Tehran Stock Exchange using hierarchical and K-means clustering methods", attempts to present a suitable method for portfolio optimization using market data and clustering. The result of this comparison will clarify the success rate of cluster optimization compared to the index portfolio.

The aim of this study is to propose a synthetic approach including Clustering and UTADIS models to form a profitable investment portfolio.

In this research, securities are clustered using K-means method and the ideal number of clusters is determined through certain validation indexes. The results obtained from the Clustering method were used as the input data for the UTADIS model and the securities were classified by UTADIS. After solving the primary model, in order to achieve better resulst, a post-optimality analysis was performed and the classification validity test and the classification error tests were carried out.

After reviewing previous studies in this field and carrying out a survey of professionals from the financial industry, eight key attributes including capital return, beta coefficient, net profit margin, BV/MV, ROA, ROE, P/E and EPS were identified. The investment portfolio consists of Iran tele companies, Khark Petrochemical, Shazand Petrochemical, Fanavaran Petrochemical, Information services, Iran refract, Khouzestan steel, and Iran zinc mines.

The results of study showed that the proposed framework has created a profitable portfolio and capital return is the most important attribute in stock portfolio selection.

Cash adequacy in banks’ branches is considered as the significant issues for branch managers; because the daily cash shortage in branches’ funds might lead to the lack of fulfilling customers’ needs. On the other hand, cash surplus in branches will increase the expenses which arise from its transfer to the banks’ treasuries. Therefore, banks have always been attempting to estimate their required cash according to their daily operations and. In this regard, iIn this article, branches of Tejarat Bank, with regard to their diversity, have been classified in similar clusters with the two methods of hierarchical clustering and clustering based on Bayesian approach .Then, based on the results obtained from the clustering, the input cash to the branches as well as the cash consumption in the branches were estimated through the neural networks, which made it possible to calculate the required cash in branches. The results show that the estimation of input and consumed cash of branches using neural network and regarding the results obtained from Bayesian approach for branches clustering enjoys higher precision in comparison to the results obtained from the classic methods of clustering.

Due to the importance of capital market, it is necessary to measure the performance of brokerage firms, as an interface among companies and investors, for enriching the quality of services.In this study, the quality of online service features through the survey literatures and the expert opinion were identified and selected. then Fuzzy Kano questionnaire design and randomly distributed between 384 online brokerage firms Users.by using the K-Means classifications, three categories of customer was identified and for each cluster, by using the fuzzy kano method, needs of each cluster were investigated and classified.The study, based on Kano model, shows classification of some features between clusters is different and for some other, for all clusters is same. In addition to, the rate of satisfaction for each feature in each cluster, as a factor, has shown the satisfaction or dissatisfaction in the presence or absence of features.The results of this study can help brokerage firms in order to provide convenient services to different customers.

Nowadays¡ Loans in the banking industry has a crucial role in productivity because a substantial portion of the assets of a bank formed though the individuals and companies. So today’s credit risk has known as a biggest contributing factor of failure in the banks and financial institutions. Because of mentioned factors¡ control and management of these risks are necessary.As it mentioned before¡ the aim of this research is a model designed for customers in the areas of Assessing credit risk rating with a synthesized MADM and SOM method. For this purpose¡ the first step is identifying 29 indices that influence credit risk. After that¡ according to expert opinion and the past researches 12 indices was extracted. So the optimal clusters were determined by neural network pattern recognition algorithm. Then customers were categorizing with SOM and K-mean. Finally¡ the relative weight of each indicator of the credit risk assessment was determined.so research show that the customer experience in the economic sectors and account duration has high percentage. Finally¡ some recommendations are offered for future research and suggestions for researchers and practitioners in the field of banking are. At the end¡ some of the limitations mentioned in this research.

There is always a considerable difference between the corporate performance and the tax levy that is identified by the taxation authorities which has become a common practice. This fact has led to no fairness among taxpayers, a fact that influences the horizontal and vertical sides of equity. Horizontal equity is created when people feel the benefits of the tax gain that is proportional to the loss of benefits. People with more financial means should also pay more taxes that is equivalent to vertical equity. One reason for the difficulty of attaining the horizontal and vertical equities is to identify the taxpayers based on their previous taxation behavior and to deal with them effectively. The aim of this study is the design of a predictive system that evaluates the corporates taxation behavior based on their previous payments. The predicting system uses key performance variables that are identified during research and it will also help in the classification of companies based on their taxation behavior into three groups of high risk, medium risk and low risk. The system is specifically designed for the taxation authorities who are attempting to effectively assessing the risk of corporate taxes gaining. In this study, the taxation clusters of customers are identified and a decision tree is designed with 80% of accuracy by the utilization of clustering and classification algorithms and effective validation methods. The resulting models of applied algorithms investigate the taxation behavior of each customer and are capable of predicting the tax payment risk of taxpayers in the future with the addition of new corporates to the list.