Word Files
Reference for Downloading Educational Files
  2. Management
  3. Determining the goals of attracting resources with the approach of fuzzy logic and neural networks in financial and credit institutions

Determining the goals of attracting resources with the approach of fuzzy logic and neural networks in financial and credit institutions

Number of pages: 159 File Format: word File Code: 30335
Year: 2016 University Degree: Master's degree Category: Librarianship
Tags/Keywords: Attract resources - Determining goals - Fuzzy logic - Neural networks
  • Part of the Content
  • Contents & Resources

  • Summary of Determining the goals of attracting resources with the approach of fuzzy logic and neural networks in financial and credit institutions

    Master's Thesis in Accounting

    Abstract:

    The power and credibility of financial and credit institutions is based on the money that depositors have deposited in them, and the progress and survival of each of the aforementioned institutions depends on the share of the total market resources, and increasing the share of the market resources requires continuous effort and a strong, comprehensive plan with a suitable model in the form of the goals of attracting total and partial resources. Since management decisions such as the selection and appointment and transfer of branch and department officials and the payment of non-continuous incomes and such things are related to the extent of achieving the goals of attracting resources and also measuring the degree of achievement of the goals of attracting resources in each of the branches of financial and credit institutions is affected by the type and extent of target setting, with the view of identifying the weaknesses of the current goal setting system in financial and credit institutions and improving the performance measurement process and preventing the reduction of the effort rate after reaching the goal and before the end of the period, in this research the amount of future resources of the branches of two financial institutions and credit with a combined approach of neural networks and fuzzy logic and creating an innovative equation and using new prediction variables and then according to the changes in the resources of each branch, goal setting was done with a constant confidence factor, and in the following, goal setting using current methods and meta-innovative methods were compared with the reality of resource attraction.

    Key words: setting goals, attracting resources, neural networks, fuzzy logic.

    Introduction

    Banking is the big industry of every country, and banks and financial and credit institutions are the places where the deposits of people are kept. There is competition between banks and financial and credit institutions to attract deposits, and comprehensive efforts such as advertising, offering higher interest payment rates for deposits, etc. In order to increase the share of market resources, it shows the principle and reality of competition.

    Banks and financial and credit institutions determine the total goals of attracting resources and communicate them to their subordinates. Information about the future regarding future resources can empower the financial and credit institution in setting goals. Information about the future is done through forecasting. From another point of view, today's world is a world of changes, and knowledge of the future and upcoming conditions and situations is an important factor in maintaining the life of financial organizations. Targeting is always done in most organizations with the attitude of achieving growth and excellence, and effective and efficient targeting can be achieved when a relatively accurate estimate and prediction of the future can be made. Forecasting has different structures and uses different methods. In this research, targeting based on forecasting has been investigated from the point of view of quantitative forecasting.

    With the advancement of science, the use of modern and intelligent forecasting methods has flourished in most financial organizations with a complex structure, and for this reason, in this research, we tried to use neural networks and fuzzy logic, and the application of combining these two methods in forecasting for targeting. The attraction of resources and its comparison with targeting without prediction should be examined.

    In this chapter, the research problem and the necessity of doing it are stated, and then the research assumptions and method. The data collection tool and its analysis method are provided. In the following, the scope of the research and the limitations and definitions of the words are given at the end.

    Statement of the research problem

    Financial and credit institutions need to attract resources for growth and excellence, and the attraction of resources by their branches in this market full of competition by providing diverse services is of great importance in expanding the volume of activities and profitability. The targeting of senior managers of financial and credit institutions has always been to expand the volume of activities and increase profitability. Managers of financial and credit institutions set goals for each of the covered branches for quarterly, six-month, or annual periods, and most of these goals are based on the ability to achieve the goals of the past periods, assigning a share of the total goal of increasing market share, the grade of each branch, and so on.

    When goal setting is based on prediction with criteria and facts, performance measurement will be more realistic. In other words, more effort and less work can be recognized.For example, if the goal of attracting resources for some branches of a financial and credit institution is lower than the usual limit and their capacity, it is not beyond imagination that the effort rate of the said branches will decrease after reaching the goal and more efforts will be focused on preserving resources until the end of the goal-setting phase, or on the contrary, the share of one branch or several branches of the goals of attracting resources is so high that it is not possible to achieve the goal with the current conditions and trends, and the efforts of the branches will not be recognized, and on the other hand Those branches have been assigned the share of attracting resources, other branches have been assigned whose effort rate has decreased after reaching the goal and with the passage of time the goal is fuel. Finance and credit need relatively accurate forecasts based on modern scientific methods for better targeting.

    Knowing the share of the future in the resource sector in budgeting and determining expenses and. It has an important and significant effect, and in general managers should try to choose a model for forecasting that meets the needs of the organization in accordance with their activities. In many cases, choosing the wrong method may lead the organization to unpleasant results. Market-based is not hidden from any individual. The banking system is always one of the most important components of the country's economy that fluctuates the growth or stagnation of the economic structure with its activity. The reason for this is the equivalence of the capital available in banks and financial and credit institutions with the main source of purchasing products and services as well as their granted loans as a source of creating credit for all economic units and enterprises. Every bank and financial and credit institution considers several indicators for the effective factors in attracting financial resources, including its deposits, and adopts a general policy for itself according to the criteria that have reached a consensus. In fact, among the factors that seem important for the survival and survival of organizations such as banks and financial and credit institutions, is the attraction of various deposits, including current loan deposits, savings loan deposits, short-term and long-term deposits, and the use of these financial resources in service, commercial, industrial and infrastructure affairs for the society. (Spanalo, 2011)

    Increasing resources is one of the things that are included in the objectives of attracting resources of financial and credit institutions, in examining the competition situation of several banks and financial and credit institutions, the bank and financial and credit institution that has a larger market share of resources is known as the market ruler, and usually weaker and smaller financial and credit institutions always try to bring their market share closer to the competitor's market share.

    In many situations, accurate data is not enough to model real-life problems; Because human judgments and preferences are vague in many situations and cannot be estimated with exact numbers. To solve this problem, fuzzy theory was proposed for the first time by Lotfizadeh, which was suitable for making decisions about uncertain and imprecise data. Because the methods of classical management science were derived from two-valued and multi-valued mathematics that require quantitative and accurate data. (Azer and Faraji, 2017)

    Knowing future situations is an important factor in determining the goals of attracting resources. Given that in many researches, future forecasting has been done by methods such as simple moving average, balanced moving average, simple smooth growth, double smooth growth, linear trend, combined function trend, and exponential trend, and its errors have been compared with the combined methods of fuzzy logic and neural networks, and the results indicate that forecasting by the combined method of fuzzy logic and neural network has less error than other methods. It is possible to use forecasting using a combination of fuzzy logic and neural networks to determine the goals of resource acquisition. Also, how to predict the future in order to target the attraction of resources with less error is one of the important topics for financial and credit institutions, and currently the use of intelligent systems to improve the quality of decisions and reduce errors has found many people all over the world.

    Forecasting the future with less error and targeting the attraction of resources based on it is one of the management tools of the branches covered by every bank and financial and credit institution, and its knowledge among banks and financial and credit institutions in Now the competition is very important and sensitive.

  • Contents & References of Determining the goals of attracting resources with the approach of fuzzy logic and neural networks in financial and credit institutions

    List:

    Table of Contents

    1 Chapter 1 - Research Plan 0

    1-1 Introduction. 1

    1-2 statement of the research problem. 2

    1-3 Necessity of doing research. 3

    1-4 hypotheses and objectives. 6

    1-4-1 hypothesis 6

    1-4-2 objectives 6

    1-5 research method. 6

    1-6 scope of research. 8

    1-7 Overview of sources in recent years. 8

    1-7-1 The relationship between resources (deposits) and expenses (facilities) 8

    1-7-2 The relationship between savings and inflation 9

    1-8 Research limitations. 11

    1-9 The general structure of the research. 12

    1-10 vocabulary definitions. 14

    2 Chapter Two - Literature and Research Background 16

    2-1 Introduction. 17

    2-2 money. 18

    2-2-1 A summary of the origin of money 18

    2-2-2 A summary of the functions and characteristics of money in society 19

    2-2-3 Terms related to money 21

    2-3  Banking. 25

    2-4 financial and credit institutions and the central bank. 27

    2-4-1 Definition of financial and credit institutions 27

    2-4-2 Objectives of financial and credit institutions 27

    2-4-3 Central Bank 28

    2-4-4 Types of banks and financial and credit institutions 29

    2-4-5 Competition of banks and financial and credit institutions in attracting resources 30

    2-5 Resource attraction. 30

    2-5-1 The concept of attracting resources 30

    2-5-2 The concept of determining the goals of resource attraction 30

    2-5-3 Factors affecting resource attraction 31

    2-5-4 The role of forecasting in determining the goals of resource attraction and performance evaluation 32

    2-6 Forecasting and its methods. 35

    2-6-1 The position of forecasting in science 36

    2-6-2 Definition of forecasting 38

    2-6-3 The location of forecasting in financial and credit institutions 38

    2-6-4 Forecasting system 38

    2-6-5 Classification of forecasting 40

    2-7 Neural network and fuzzy logic. 45

    2-7-1 neural network. 45

    2-7-2 fuzzy logic 57

    2-7-3 neural network - fuzzy 61

    2-8 background. 65

    2-8-1 Internal Background 65

    2-8-2 External Background 74

    3 Chapter Three - Research Method 81

    3-1 Introduction. 82

    3-2 research methodology. 82

    3-3 statistical population. 84

    3-4 methods of collecting information. 84

    3-5 How to prepare data 84

    3-5-1 Data collection and data equalization 85

    3-5-2 Data cleaning 85

    3-5-3 Feature selection 87

    3-5-4 Sampling 87

    3-5-5 Data transformation 88

    3-6 Review of research variables. 90

    3-6-1 Theories of money demand 90

    3-6-2 Variables affecting resources 93

    3-7 Structure of neural-fuzzy network. 98

    3-8 prediction structure. 98

    3-9 The structure of setting goals. 99

    4 Chapter Four - Data Analysis 101

    4-1 Introduction. 102

    4-2 fuzzy neural network. 102

    4-3 Implementation. 102

    4-3-1 Fuzzy neural network model design 102

    4-3-3 model implementation 103

    4-4 information analysis method. 103

    4-5 Measuring the amount of error in forecasting. 104

    4-6 Measuring the amount of deviation in determining the goals of attracting resources. 105

    4-6-1 Deviation of realized resources with targeting according to the current method 105

    4-6-2 Deviation of realized resources with targeting based on 150% forecast 105

    5 Chapter 5 - Results and suggestions 106

    5-1 Introduction. 107

    5-2 Checking the results of the prediction system. 107

    5-3 Checking the results of the targeting system. 108

    5-4 Checking the hypothesis and objectives. 111

    5-5 Conclusion. 115

    5-6 suggestions. 118

    6 List of sources 119

    7 Appendices 124

     

    List of tables

    Table No. 2-1: Actual performance-targeting by normal method (current method)-targeting based on 150% forecast. 32

    Table No. 2-2: History of neural network. 46

    Table No. 3-2: Summary of internal backgrounds. 65

    Table No. 4-2: Continued summary of internal backgrounds. 66

    Table No. 5-2: Summary of foreign backgrounds. 74

    Table No. 6-2: Continued summary of foreign backgrounds. 75

    Table No. 1-3: Dates of data 97

    Table No. 1-5: The total forecast error of future resource balance and actual realized resource balance in both financial and credit institutions. 107

    Table No. 5-2: Total error between107

    Table No. 2-5: The total error between targeting based on the current method and the actual attracted resources in both financial and credit institutions. 109

    Table No. 3-5: The total targeting error based on 150 percent forecast and actual attracted resources in both financial and credit institutions. 110

    Table No. 4-5: Comparison of the error of setting goals using the current method and setting goals based on 150 percent prediction 111

    Table No. 5-5: Comparison of the average absorption or deduction of resources around the goal-setting method in two institutions A and B with the amount of reality 113

    Table No. 6-5: Relationships between variables. 116

    Table No. 5-7: Continued relationships between variables. 117

    Appendix No. 6-1: Table of results in financial and credit institution A. 125

    Appendix No. 2-6: Continuation of the table of results in financial and credit institution A. 126

    Appendix No. 3-6: Continuation of the table of results in financial and credit institution A. 127

    Appendix No. 4-6: Continuation of the table of results in financial and credit institution A. 128

    Appendix No. 5-6: Continuation of the table of results in financial and credit institution A. 129

    Appendix No. 6-6: Continuation of the table of results in the financial and credit institution b. 130

    Appendix No. 6-7: Continuation of the table of results in financial and credit institution b. 131

    Appendix No. 6-8: Continuation of the table of results in financial and credit institution B. 132

     

     List of forms

    Figure 1-1: Chart related to the profit of financial and credit institutions, inflation and real interest rate. 11

    Figure No. 1-2: Research structure chart. 13

    Figure No. 2-1: Actual performance-Targeting of the normal method (current method)-Targeting based on 150% prediction-Example 1. 33

    Figure No. 2-2: Actual performance-Targeting of the normal method (current method)-Targeting based on 150% forecast-Example 2. 34

    Figure number 2-3: Prediction system) Jafarnejad-1385 (39

    Figure number 2-4: The structure of a neuron (Wikipedia) 47

    Figure number 2-5: Mathematical function of a neuron (basics of neural networks), Mohammad Baqer Minhaj, Amirkabir Sanani University, 4th edition, Tehran, 2011, page 43) Figure 2-6: The structure of a recurrent network. Figure 2-7: Activation functions used in neural networks. Figure 2-8: Feedforward neural network (SV Cartalops, Fuzzy Logic and Neural Networks.) 55 1-5: The error diagram between the forecast of future resources and the actual realized resources balance in both financial and credit institutions. Figure 5-2: The error diagram between targeting based on the current method and the actual absorbed resources in both financial and credit institutions. 109

    The error diagram of targeting based on 150 percent of the actual absorbed resources in both financial institutions. 110

    Source:

    List of references

    Nadri, Ismail, "Chaos analysis, wavelet analysis and neural network in predicting the Tehran Stock Exchange", 2011

    Azer, Adel and Faraji, Hojjat, Science of Fuzzy Management, Tehran: Merhaban Nashr, 2017.

    Rajaskarnaviji and Alakshmi Pai, Neural Networks. Fuzzy Logic and Genetic Algorithm: Synthesis and Application, translated by Mahmoud Keshavarzamehr, Tehran: Nofardazan Publishing House, 2013.

    Spanalo, H., "Analysis of Factors Affecting Bank Deposits (Case Study of Bank Mellat)", Mazandaran University of Science and Technology, 2013.

    Azar, Afsar, "Modeling stock price index prediction using fuzzy neural networks", Journal of Business Research, No. 40, 1385.

    Azer, Afsar and Ahmadi, "Comparison of classical methods and artificial intelligence in forecasting the stock price index and designing a hybrid model", Modares Humanities Journal, Volume 10, 30, 1385.

    Ramazanian, Mohammad Rahim and Ramadanpour, Ismail and Pourbakhsh, Seyed Hamed, "New approaches in forecasting using neural-fuzzy networks: Oil price", Gilan University, 2018.

    Kurdestani, Gholamreza and Masoumi, Javad and Baqaei, Vahid, "Prediction of profit level management using artificial neural networks", Journal of Accounting Advances of Shiraz University, Volume 5, consecutive 3/64, 2018.

    Fadaei, Mohammad, Investigation of factors affecting the mobilization of banking resources, Iran and the World Money and Financial Market Analytical Database 2013.

    Azer, Rajabzadeh, "Evaluation of hybrid forecasting methods: performance of classical neural networks in the field of economics", Economic Research, No. 63, 2013.

    Nejadmoghadam, Qasim and Baghainia, Fatemeh and Bafandeh, "Fuzzy logic in simple language", Sanat Avhavi magazine, No. 119, 2011.

Determining the goals of attracting resources with the approach of fuzzy logic and neural networks in financial and credit institutions
How To Access The File
Related Contents:
Number of pages: 136 Category: Management

Master's thesis in the field of business management, financial orientation. Abstract In this research, as an example, forecasting the timing of stock transactions of 17 active companies in the Tehran Stock Exchange was carried out. In this way, firstly, the primary data, which includes 3 variables of the final price, the lowest price and the highest stock price during the period ...

Number of pages: 117 Category: Civil Engineering

Master's thesis in the field of civil engineering - hydraulic structures Abstract: Rivers are one of the most important and common sources of drinking, agricultural and industrial water supply. These resources have many qualitative fluctuations due to passing through different platforms and direct connection with the surrounding environment. Therefore, predicting the quality of ...

Number of pages: 125 Category: Geography - Urban Planning

Master's Thesis on Natural Resources - Desertification Abstract Mangrove forests are located in the southern coastal areas of Iran, and due to their numerous functions and environmental values, it is necessary to protect, restore and develop them. Deciding the way to act in a certain way is consciously to achieve the goals, so as to choose a suitable option among various ...

Number of pages: 88 Category: Geography - Urban Planning

Dissertation for Master's Degree (M.Sc.) Investigating the application of artificial neural network method in estimating the annual runoff of watersheds (Case study: Total Watershed, Fars Province) by: Jalal Zarei Abstract: The importance and place of water in human life, especially in the modern and overpopulated world, is not hidden from anyone, and industrial and urban life ...

Number of pages: 88 Category: Computer Engineering

Non-continuous master's degree in computer engineering Abstract Today, the popularity of social networking sites among people is undeniable, sites that provide users with many possibilities for communication between people. One of the basic problems in analyzing these types of networks is predicting new connections between people in the network. Fuzzy method, as one of the ...

Number of pages: 156 Category: Social Sciences - Sociology

The abstract of the current research was conducted with the aim of knowing the role of the internal factors of the newsroom on the quantity and quality of television news. In this research, which was conducted through a survey method by distributing a questionnaire among a statistical sample of the employees of the Central News Unit of the Islamic Republic of Iran; The ...

Number of pages: 303 Category: Geography - Urban Planning

Dissertation for obtaining a doctorate degree in the field of geography and rural planning. Dissertation/dissertation abstract: The development of the agricultural sector in rural areas is based on the existence of natural talents and the realization of planning goals for the establishment of development facilities and requirements. This is despite the fact that some rural ...

Number of pages: 330 Category: Management

Dissertation for Ph.D. Abstract Statement of the Problem The purpose of this research was to design a generic model of strategic partnership in the banking and insurance industry based on the process of value creation and allocation. The main issue in conducting this research is the ever-increasing intensification in the competitive environment and the application of ...

Number of pages: 105 Category: Geography - Urban Planning

Dissertation for Master's Degree in Natural Geography Abstract Iran is a vast country that, due to its special location and topographic features, lacks water and It has a different atmosphere. For this reason, most of Iran is in the dry climates of the world. In addition to the lack of rainfall, the extreme fluctuations of rainfall in daily, seasonal and annual scales are among ...

Number of pages: 85 Category: Biology - Environment

Dissertation for M.Sc. Natural Resources Engineering, Watershed Management Abstract Currently, flood spreading on aquifers is considered one of the suitable methods for controlling and optimal use of floods and artificial feeding of groundwater in arid and semi-arid areas. Chenaran watershed in the northwest of Mashhad with an area of ??299,624 hectares is located at 36.36 19.59 ...