Date: College Seal ABSTRACT In our banking system, banks sell many products, but credit lines are the main source of income for any bank. So they can earn interest on credited loans, A bank's profit or loss is highly dependent on its creditworthines i.e, whether its customers repay loans or default. By predicting loan defaults, banks can reduce their bad assets. This makes the study of this phenomenon very important. Previous research from this era indicates that there are a great many ways to study the problem of credit default management. However, correct prediction is so important to maximize profit that it is essential to study the properties of different methods and how they compare, A very important approach in predictive analytics is used to study the problem of predicting loan defaults: the logistic regression model, Data is collected by Kaggle for research and prediction. A logistic regression model was run and various performance indicators were calculated. Models are compared using performance measures such as sensitivity and specificity. The final results showed that the models gave different results. The model is slightly better because it includes variables (personal characteristics of the customer such as age, purpose, credit history, loan amount, loan tenure, etc.) (© scanned wt onENScnnerACKNOWLEDGEMEN We would like to express our special thanks and gratitude to our project guide Mrs. Aasha (Chavan for guiding us to do the project work on time and giving us all support and guidance, which made complete our project duly. We are extremely thankful to her for providing such nice support and guidance. We are also thankful for and fortunate enough to get constant encouragement, support and guidance from the teachers of information Technology who helped us in successfully completing our project work © scone wine scarDECLARATION hereby declare that the project entitled, “Loan Prediction System” done at Vidyalankar School of Information Technology, has not been in any case duplicated to submit to any other universities for the award of any degree. To the best of my knowledge other than me, no one has submitted to any other university ‘The project is done in partial fulfillment of the requirements for the award of degree of BACHELOR OF = SCIENCE (INFORMATION TECHNOLOGY) to be submitted as final semester project as part of our curriculum, Name and Signature of the Student © scone wine scarTable of Contents Contents Chapter 1 Introduction 12 Objectives 8 13 Purpose, Scope, and Applicability 7 oe 1.3.1 PURPOSE “9 1.3.2 Scope 8 133 APPLICABILITY 10 Languages to be used Ea Fry 3 Problem Definition 32 Requirement Specification 15 3.3 Software and Hardware Requirement 16 33 Planning and Scheduling v7 CHAPTER 4: SYSTEM DESIGN 1 18 4a Integrity and Constraints 18 42 Diagrams 19 4.2.1 Block Diagram. 4.2.2 Use Case Diagram 20 © scone wih one came4.2.3 Testing Model. 4.2.4 Modular Diagram. 4.2.5 Class Diagram 23 Websites 24 Plagiarism Report 25 © scone wih one cameCHAPTER 1: INTRODUCTION 1.1 Background Distribution of the loans is the core business part of almost every bank. ‘The main portion Of the bank’s assets directly came from the profit earned from the loans distributed by the banks. The prime objective in the banking environment is to invest their assets in safe hands where itis. Nowadays many banks‘finance firms give loans after a regress process of authentication Validation but still there is no guarantee whether the chosen applicant is the deserving right for Applicant out of all applicants. ‘Through this system we can predict whether that particular and Applicant is safe or not and the whole process of validation of features is automated by machine Learning technique. With this model we can predict whether that specific applicant is prudent or Not. Loan Prediction is very helpful for employees of banks as well as for the applicant also,The Aim of this system is to provide a quick, immediate and easy way to choose the deserving Applicants The two most critical questions in the lending industry are: 1) How risky is the borrower? 2) Given the borrower's risk, should we lend him/her (© scanned wt onENScnner1.2 Objectives Due to the large size of some banks, overexposure to risk can cause bank failure and Impact millions of people. By understanding the risks posed to banks, governments can set better Regulations to encourage prudent management and decision-making. The ability of a bank to Manage risk also affects investors’ decisions. Even if a bank can generate large revenues, lack of Risk management can lower profits due to losses on loans. Value investors are more likely to Invest in a bank that is able to provide profits and is not at an excessive risk of losing money. ‘There are times where high reputed banks even fail in identifying the tight person while giving a Loan. Thus, the project focuses on identifying the right person at a very early stage. Loan Prediction system is a system which provides you a interface for loan approval to the applicants application of loan. Applicants provides the system about their personal information and according to thei information system gives his status of availability of loan. 1.3 Purpose, Scope, and Applicability 1.3.1 PURPOSE When choosing an applicant for loan approval, they must take into ies. The bank has to choose which is ideal for account a few bank pol approval based on a few criteria. To manually check out each person before recommending them for loan approval is difficult and dangerous. Based on the prior performance of the person to whom the loan amount was previously accredited, we utilise a machine leaning technique in this study to forecast the person who is trustworthy for a loan, The main (© scanned wt onENScnner‘goal of this project is to determine whether or not approving a loan to a certain person is safe 1.3.2 Scope ‘The project basically starts with a web-based application which acts as a middleman between the user and our training model. The system is designed in such a way that the input will be taken from the user by a form and that data will be used for training our model. The model is designed with the help of logistic regression which provides better efficiency in training the model as well as is easy to implement. 1.3.3 APPLICABILITY For development of the application, we have used the agile model as it helps in fast delivery of the system. Agile SDLC model is a combination of iterative and incremental process models with focus on process adaptability and customer satisfaction by rapid delivery of working software products. Agile Methods break the product into small incremental builds. These builds are provided in iterations. Each iteration typically lasts from about one to three weeks. Agile models help toimprove quality and focus on Business Value and users. Every iteration involves cross functional teams working simultaneously on various areas like, - Planning - Requirements - Design «Coding - Unit Testing and - Acceptance Testing 10 (© scanned wt onENScnnerCHAPTER 2: SURVEY OF TECHNOLOGY Languages to be used HTML HTML The Hyper Text Markup Language or HTML is the standard markup language for documents designed to be displayed in a web browser. It can be a ted by technologies such as Cascading Style Sheets (CSS) and scripting languages such as JavaScript. Web browsers receive HTML documents from a web server or from local storage and render the documents into multimedia web pages. HTML describes the structure of a web page semantically and originally included cues for the appearance of the document, HTML elements are the building blocks of HTML pages. With HTML constructs, images and other objects such as interactive forms may be embedded into the rendered page. HTML provides a means to create structured documents by denoting structural semantics for text such as headings, paragraphs, lists, links, quotes and other items. a (© scanned wt onENScnnerHTML can embed programs written in a scripting language such as JavaScript, which affects the behaviour and content of web pages. Inclusion of CSS defines the look and layout of content. The World Wide Web Consortium (W3C), former maintainer of the HTML and current maintainer of the CSS standards, has encouraged the use of CSS over explicit presentational HTML since 1997. A form of HTML, known as HTMLS, is used to display video and audio, primarily using the element, in collaboration with java script. css Cascading Style Sheets (CSS) is a style sheet language used for describing the presentation of a document written in a markup language such as HTML or XML (including XML dialects such as SVG, MathML. or XHTML).CSS is a comerstone technology of the World Wide Web, alongside HTML and JavaScript. The CSS specifications are maintained by the World Wide Web Consortium (W3C). Internet media type (MIME type) text/ess is registered for use with CSS by RFC 2318 (March 1998). ‘The W3C operates a free CSS validation service for CSS documents. 2 (© scanned wt onENScnnerHTTP is a first-class citizen in Node. js, designed with streaming and low latency in mind. This makes Node,js well suited for the foundation of a web library or framework. PYTHON Python is a high-level, general-purpose programming language. Its design philosophy emphasizes code readability with the use of significant indentation, Python is dynamically typed, and garbage collected. It supports multiple programming paradigms, including structured, object- oriented and functional programming. Itis often described as a “batteries included” language due (0 its comprehensive standard library. ADVANTAGES It’s Simple. Its Free, It's Easy to Use. B (© scanned wt onENScnnerIts Hi Itis Object-Oriented. ly Compatible. Ithas Lots of Libraries. Ithas Built-in Data Structures. Its Widely Applicable. JavaScript JavaScript JavaScript often abbreviated as JS, is a programming language that is one of the core technologies of the World Wide Web, alongside HTML and CSS. As of 2022, 98% of websites use JavaScript on the client side for webpage behaviour, often incorporating third party libraries. All major web browsers have a dedicated JavaScript engine to execute the code on users’ devices. JavaScript is a high-level, often jus time compiled language that conforms to the ECMAScript standard. It has dynamic typing, prototype-based object-orientation, and firstclass functions. It is multi- paradigm, supporting event-driven, functional, and imperative programming styles. It has application programming interfaces (APIs) for working with text, dates, regular expressions, standard data structures, and the Document Object Model (DOM). 4 (© scanned wt onENScnner‘The ECMAScript standard does not include any input/output (/O), such as networking, storage, or graphics facilities. In practice, the web browser or other runtime system provides JavaScript APIs for VO JavaScript engines were originally used only in web browsers, but ‘are now core components of some servers and a variety of applications, ‘The most popular runtime system for this usage is Node,js. Although Java and JavaScript are similar in name, syntax, and respective standard libraries, the two languages are distinct and differ greatly in design. CHAPTER 3: REQUIREMENTS AND ANALYSIS 3.1 Problem Definition A web-based application which predicts whether a loan will be approved or not for an enduser. There are different types of loans like (Personal Loans, Home Loans, Mortgages Loans etc...) Our web-app focuses only on one product ice., Personal Loans. Web-app will be based on different web technologies, Python and Machine Learning. In machine learning we apply decision tree algorithms in which all attributes or features should be discretized. Attribute selection is based on significant information gain of features. The product will begin in a way that it will start by supplying data to the machine learning model, based on this data set the model is trained. All new candidate details are filled at the time of application form and acts as a test da a set. After the testing operation, the system will guess whether the new applicant is a fit case for approval 15 (© scanned wt onENScnnerof the loan or not based upon the conclusion it concludes because of the training data sets. The basic data set should have attributes like the loan id, education, selfemployed, salary, previous loan history, credit score, Joan amount etc. Thus, our prediction model will require the above data to produce accurate results, 3.2 Requirement Specification FUNCTIONAL REQUIREMENTS: ‘The system consist User model and ML model which help for * USER: ‘The system shall authenticate the user and then display the panel based on the particular identified user. Login: Users need to log in using their valid login credentials in order to access the web application © Add personal details: In this function the user can enter their personal details and this data set acts as the training data set In this section the user can add all Loan details View details: Users can view all the enter details at dashboard NON-FUNCTIONAL REQUIREMENTS: © Usability ‘There is a consistency in all the modules. To ease the navigation there is a back tab to provide access to the previous page. There is proper instruction on each page. # Reliability: 16 (© scanned wt onENScnnerEach data record is stored on a well-built efficient database schema. There is no risk of data loss. The internal evaluation of data is well coded. © Supportability: The system is well built to support any machine. Maintainability of the system is easy. ¢ Performance: In order to ease the accessibility, the types of expenses are categorized along with an option to name on their own. Throughput of the system is increased due to light weight database support. 3.3 Software and Hardware Requirement « Hardware Requirements: » 4 Cores 8 Threaded processor > 8GB RAM minimum > 4GB GPU minimum + Software Requirement > Web based Technologies ( HimlS, css3, JavaScript, bootstrap4, react, Angular js) > Python 3.7 or greater than 3.4 > Flask for Imegration > Libraries of Python (pandas, Matplotlib, NumPy etc...) 3.3 Planning and Scheduling Project Planning: Software project plan can be viewed as the following: v7 © scone wine scarFor a successful software project, the following steps can be followed: Select a project Identifying project's aims and objectives ‘Understanding requirements and specification ‘Methods of analysis, design and implementation Testing techniques Documentation Project milestones and deliverables Budget allocation Exceeding limits within control Sener Dear ia wio [wa wtf ee ‘een we ie Fain Sve al ed eae) Fenbity andre ite Spee eCoes Sie inte ope Dt Dig Bak Dagar Dagon Ky Da Sate (rN Dogars eee Act ow Cit ee) Cage Hee ala Tee [ees = i Teil me no Fate ongFshoe Reson Does Pan eae Deen ah ae Figure 13.3 Gantt Chart 44 Software and Requirement © scanned wth onEN ScannerCHAPTER 4: SYSTEM DESIGN 4.1 Data Integrity and Constraints © Colum Non-Nuil Count Loan_I0 614 non-null. e 1 Gender 681 non-null 2 Married 611 non-null 3 Dependents 599 non-null 4 Education 616 non-null 5 Self Employed 582 non-null 5 Applicantincome 614 non-null 7 Coapplicantincome 614 non-null 8 Loandnount 592 non-null 9 Loan_Amount_Term 600 non-null. 10 Credit History 564 non-null 11 Property Ares) 616 non-null 12 Loan status 614 non-null types: Floatea(4), intsa(1), object(s) memory usage: 62.5+ KS ee ee ed Dtype object object object object object object inte floates Floates floates floates object object 2 wens woe we © cea w 3 von won we © onal ~ BR ERE 19 © scanned wth onEN Scanner4.2 Diagrams 4.2.1 BLOCK DIAGRAM OF THE PROPOSED SYSTEM: Figure 4.1.1 System architecture block diagram The figures show the flow of the loan prediction system. Firstly we developed a web Application that acts as a bridge between the user and our training model. All data we get from a Web application that act as input to data processing in that we perform data completion In the Data completion there are often missing values in the dataset due to improper data entry or the Data entry problems that can lead to issues in data analysis, thereby affecting the accuracy of the System and after the pre 20 © scanned wth onEN Scannerprocessing and testing operation, the system will guess whether the new Applicant is a fit case for approval of the loan or not based upon the algorithm. It concludes on The basis of the training data sets. 4.2.2 Use Case Diagram ‘System: \2 ae 21 © scanned wth onEN Scanner4.2.3 TRAINING AND TESTING MODEL: © scanned wth onEN Scanner