ABSTRACT
Credit risk evaluation is an important and interesting problem in financial analysis domain. Credit risk evaluation has been the major focus of financial and banking industry. An accurate estimation of credit risk could be transformed into a more efficient use of economic capital. Several techniques like expert systems, decision tree etc. have been used for credit rating. However, these method have limitations of knowledge bottleneck, slow learning etc. recently artificial neural networks (ANN) has been proposed as the while-box models for classifying creditors.
In this research work, I try to apply the artificial neural networks (ANN) and its genetic algorithms to design a credit risk evaluation system to discriminate good creditors from bad ones. The efficiency of classification is evaluated in terms of classification errors calculated from the actual classification made by the credit officers. The result of the experiment shows how the application of an artificial neural network system can support the creditworthiness evaluation of borrowers.
TABLE OF CONTENTS
ABSTRACT
CHAPTER ONE
1.0 INTRODUCTION
1.1 STATEMENT OF PROBLEM
1.2 OBJECTIVE OF THE STUDY
1.3 SCOPE OF THE STUDY
1.4 DEFINITION OF TECHNICAL TERMS
CHAPTER TWO
2.0 LITERATURE REVIEW
2.0.1 SCENARIO
2.1 THEORETICAL BASIS
2.1.1 CONSUMER CREDIT
2.1.2 RIST OF CREDIT
2.1.3 EVALUTION OF THE RISK OF CREDIT
2.1.4 CREDIT SCORING MODELS
2.2 FUNCTIONS OF A CREDIT RISK RATING SYSTEM
2.3 DEVELOPMENTS IN BANK RISK RATING SYSTEMS
2.4 REVIEWING AND UPDATING CREDIT RISK RATINGS
2.5 THE CREDIT RISK EVALUATION PROCESS
2.6 CREDIT RISK MITIGATION
2.6.1 COLLATERAL
2.6.2 LOAN GURANTEES
2.6.3 LETTERS OF CREDIT
2.6.4 CREDIT DERIVATIVES
2.6.5 CREDIT INSURANCE
2.7 UTILIZED TECHNIQUES
CHAPTER THREE
3.0 ALGORITHM AND LOGIC DESIGN (FLOWCHART)
3.1 ALGORITHM
MAIN PROGRAM MODULE
NEW APPLICATION MODULE
LOAN SCHEDULE MODULE
RETRIEVE RECORD MODULE
UPDATE RECORD MODULE
DISPLAY REPORT MODULE
LOAN HISTORY MODULE
CRATED USER ACCOUNT MODULE
LOG OFF USER ACCDOUNT MODULE
3.2 LOGIC DESIGN (FLOWCHARTS)
FLOWCHART FOR MAIN MODULE
CREATE USER ACCOUNT MODULE
NEW APPLICATION MODULE
LOAN SCHEDULE MODULE
RETRIEVE RECORD MODULE
UPDATE RECORD MODULE
VIEW REPORT MODULE
LOAN HISTORY MODULE
LOG OFF ACCOUNT MODULE
CHAPTER FOUR
4.0 SOURCE CODE, SMAPLE OUTPUT, REASONS FOR CHOICE OF LANGAUGE AND HOW TO RUN THE PROGRAM
4.1 SOURCE CODE
4.2 SAMPLE OUPUT
4.3 HOW TO RUN THE PROGRAM
4.4 REASONS FOR USING VISUAL BASIC PROGRAMMING
4.5 LANGUAGE
CHAPTER FIVE
5.0 SUMMARY
5.1 CONCLUSION
5.2 RECOMMENDATIONS
5.2.1 LIMITATIONS
5.2.2 RECOMMENDATIONS
REFERENCES
CHAPTER ONE
1.0 INTRODUCTION
Credit-Risk evaluation is a very challenging and important data mining problem in the domain of financial analysis. One of the key decisions financial institutions have to make is to decide whether or not to grant a loan to a customer. This decision basically boils down to a binary classification problem which aims at distinguishing good payer from bad payers.
Until recently, this distinction was made using a judgmental approach by merely inspecting the application form details of the applicant. The credit expert then decided upon the creditworthiness of the applicant, using all possible relevant information concerning his / her socio-demographic status, economic conditions and intensions. The advent of data storage technology has facilitated financial institutions ability to store all information regarding the characteristics and repayment behaviour of credit applicants electronically. This has motivated the need to automate the credit-granting decision by using machining-learning algorithm or artificial neural networks.
Numerous methods have been proposed in the literature to develop credit-risk evaluation models, these models include; Traditional statistics methods (e.g. logistic regression), nonparametric statistical models (e.g. K-nearest neighbor and classification trees) and Neural network models. Most of these studies focus primarily on developing classification models with high predictive accuracy without paying any attention to explaining how the classifications are being made. Clearly, this plays a pivotal role in credit-risk evaluation, as the evaluator may be required to give a justification for why a certain credit application is approved or rejected. Capon (1999) was one of the first authors to argue that credit-risk evaluation system should focus more on providing explanations for why customers default instead of merely trying to develop score cards which accurately distinguish good customers from bad customers.
Financial institute such as banks, leasing companies, investment and pension funds are subject to financial risk. The main risks are: Credit, Market, Liquidity and Operational risk. To reduced credit risk, financial institutions perform an economic analysis of each potential borrower.
In this research work, I report on the use of Artificial Neural Network rule extraction techniques to build intelligent and self explanatory credit-risk evaluation system. Although artificial neural networks have been used before for this purpose, there is still no consensus on their superiority with respect to more traditional statistical algorithms such as logistic regression. This refers to the fact that they do not allow formalization of the relationship between the outputs and the inputs in a user-friendly, comprehensible way.
1.5 STATEMENT OF PROBLEM
Traditionally, credits are granted based on a judgmental concept using past experiences of the credit officers. This approach suffers, however, from: High cost of training credit officers; frequent incorrect decisions made by credit officers; the long period of time that is required to evaluate the risk category of the client and to make the credit granting decision; and different decisions (made by different credit officers) for the same case.
These numerous difficulties suggest the need to automate credit management decisions.
Against this background, Artificial Neural networks intelligence technologies have been employed for the development of credit-risk evaluation software system that can meet the emerging needs and requirement.
1.6 OBJECTIVE OF THE STUDY
Recent developments in algorithms that extract rules from trained neural networks enable us to generate classification rules that explain the decision process of the network. The purpose of my research is to investigate whether these artificial neural network rule extraction techniques can generate meaningful and accurate rule sets for the credit-risk evaluation problem
1.7 SCOPE OF THE STUDY
In the field of computing today, there are basically different types of techniques or methods used in solving different kinds of problems. However, this project is designed mainly to deal with credit-risk problem in financial institutions (Banks) using Artificial Neural Networks and its generic algorithms to evaluate the credit-worthiness of an applicant in other to grant loan to that individual. And finally, to formalize the context in which this method could be applied.
1.8 DEFINITION OF TECHNICAL TERMS
CREDIT: Credit is borrowed money that you can use to purchase things you need when you them and then repay the funds back at an agreed on time.
RISK: A state of uncertainty where some of the possibilities involve a loss, catastrophe, or other undesirable outcome. Or it is the quantifiable likelihood of loss or less-than expected returns.
LOAN: Loan is a certain amount of money given for a certain period of time. It is repaid according to the set schedule.
EVALUATION: The process of determining whether an item or activity meets specified criteria.
COLLATERAL: It is any asset that is pledged, hypothecated, or assigned to the lender and that the lender has the right to take possession of, if the borrower defaults.
NEURAL NETWORKS: in information technology a Neural Network is a system of programs and data structures that approximates the operation of the human brain.
Buyers has the right to create
dispute within seven (7) days of purchase for 100% refund request when
you experience issue with the file received.
Dispute can only be created when
you receive a corrupt file, a wrong file or irregularities in the table of
contents and content of the file you received.
ProjectShelve.com shall either
provide the appropriate file within 48hrs or
send refund excluding your bank transaction charges. Term and
Conditions are applied.
Buyers are expected to confirm
that the material you are paying for is available on our website
ProjectShelve.com and you have selected the right material, you have also gone
through the preliminary pages and it interests you before payment. DO NOT MAKE
BANK PAYMENT IF YOUR TOPIC IS NOT ON THE WEBSITE.
In case of payment for a
material not available on ProjectShelve.com, the management of
ProjectShelve.com has the right to keep your money until you send a topic that
is available on our website within 48 hours.
You cannot change topic after
receiving material of the topic you ordered and paid for.
Login To Comment