Prediction of Credit Card Approval

Credit risk as the board in banks basically centers around deciding the probability of a customer's default or credit decay and how expensive it will end up being assuming it happens. It is important to consider major factors and predict beforehand the probability of consumers defaulting given their conditions. Which is where a machine learning model comes in handy and allows the banks and major financial institutions to predict whether the customer, they are giving the loan to, will default or not. This project builds a machine learning model with the best accuracy possible using python. First we load and view the dataset. The dataset has a combination of both mathematical and non-mathematical elements, that it contains values from various reaches, in addition to that it contains a few missing passages. We preprocess the dataset to guarantee the AI model we pick can make great expectations. After the information is looking great, some exploratory information examination is done to assemble our instincts. Finally, we will build a machine learning model that can predict if an individual's application for a credit card will be accepted. Using various tools and techniques we then try to improve the accuracy of the model. This project uses Jupyter notebook for python programming to build the machine learning model. Using Data Analysis and Machine Learning, we attempted to determine the most essential parameters for obtaining credit card acceptance in this project. The machine learning model we built gave an 86 % accuracy for predicting whether the credit card will be approved or not, considering the various factors mentioned in the application of the credit card holder. Even though we achieved an accuracy of 86%, we conducted a grid search to see if we could increase the performance even further. However, using both the machine learning models: random forest and logistic regression, the best we could get from this data was 86 percent.

Design and Development of Lanyard Printing Machine

A Lanyard is an essential part of preparing any company or Organization’s office supplies or stationery. As an ID card holder, Lanyard provides identity and respectability to different organizations. While a simple lanyard is surely practical, a printed and specialized one will undoubtfully leave an enduring effect. To get attractive, brand-relevant satin lanyards to give your company just the right kind of exposure it needs and if employees are participating in conferences and exhibitions, wearing a branded lanyard will help them increase brand awareness. The work involved the design, development, and testing of a Lanyard Printing machine which overcomes the drawback of existing costly printing machines. The design and developmental stages include the gear and chain drive along with the rack and pinion method and their generation mechanisms. Details of a simple, sturdy, and efficient gear and chain unit, financially beneficial to laborers and producers are considered. The unit can print about 80 impressions per minute compared to 30 impressions per minute of existing machines.

Nudging Commuters to Increase Public Transport Use: A Field Experiment in Rotterdam

A large-scale field experiment in Rotterdam, Netherlands, tested whether nudging could increase public transport use. During one work week, 4000 commuters on six bus lines, received a free travel card holder. On the three bus lines in the experimental condition, the card holders displayed a social label that branded bus passengers as sustainable travelers because of their bus use. On the three bus lines in the control condition, there was no such message on the card holders. Analysis of the number of rides per hour showed that the intervention led to a change from pre-intervention (619 days) to post-intervention period (176 days) that was estimated to be 1.18 rides per day greater on experimental lines than on control lines. This experiment shows that public transport operators can increase public transport use by incorporating messages that positively label passengers as sustainable travelers in their communication strategies.

PERLINDUNGAN HUKUM TERHADAP PEMEGANG KARTU KREDIT DALAM TRANSAKSI PERBANKAN

Perlindungan terhadap nasabah dapat menjadi tidak jelas, dimana pada akhirnya dapat mengakibatkan masalah-masalah yang timbul dari transaksi tersebut, Bahkan nasabah sering berada dalam pihak yang dirugikan, misalnya transaksi dengan menggunakan kartu kredit, adanya transaksi yang tidak pernah dilakukan sebelumnya oleh pemilik kartu kredit namun yang terjadi adanya pemberitahuan dari pihak bank mengenai tagihan kartu kredit tersebut, perhitungan kredit limit atau saldo yang salah sehingga pemegang kartu kredit membatalkan transaksi belanja mereka, adanya keluhan dari nasabah mengenai suku bunga yang tidak sesuai, hal ini jelas sangat merugikan nasabah pada saat melakukan transaksi dan tagihan kartu kredit melebihi harga yang dibayar oleh konsumen. Jenis penelitian yang digunakan dalam penulisan penelitian ini adalah penelitian hukum Normatif. Dari hasil penelitian dapat disimpulkan belum terlaksana dengan baik karena adanya transaksi yang tidak pernah dilakukan sebelumnya oleh pemilik kartu kredit namun yang terjadi adanya pemberitahuan dari pihak bank mengenai tagihan kartu kredit tersebut, perhitungan kredit limit atau saldo yang salah sehingga pemegang kartu kredit membatalkan transaksi belanja mereka, adanya keluhan dari nasabah mengenai suku bunga yang tidak sesuai pada saat perjanjian, hal ini jelas sangat merugikan nasabah pada saat melakukan transaksi dan tagihan kartu kredit melebihi harga yang dibayar oleh konsumen. Hambatan dan Upaya adalah dilihat dari sisi pelaku usaha, dilihat dari sisi nasabah selaku konsumen, dilihat dari sisi lain, kurang berperannya pihak-pihak yang terkait dengan perlindungan terhadap nasabah dan upaya yang dilakukan untuk terhadap perlindungan hukum tersebut adalah meningkatkan kesadaran pelaku usaha (nasabah) dan tahap mediasi. Bank dalam memberikan perlindungan kepada pemegang kartu kredit (card holder), harus lebih menitik-beratkan pada pembuatan produk kartu kredit.

Assessing Financial Transaction Bank Credit Cards According to Islamic Banking System

This research explored the historical background to bank credit cards, the development of using plastic cards, classification of bank cards, characteristics and benefits of each class of cards. The research intends to address presumed problems such as: what are bank credit cards? How it has been developed? What are the international organization that introduced plastic cards? How these companies settle the payment between the card holder, the bank where he opened account and the business center, where he purchased goods or enjoyed services? Descriptive analytical methodology was employed for analysis whereby the research described type of bank cards, classified them and then collaborate analysis with the usage and benefits of each card. The thrust of the paper is to explore the views of Shariah Law pertaining the legality of using plastic bank credit cards, describing the acts and behavior which is not lawful according to provisions of Shariah Law. Moreover it includes the legal basis for collecting fees by bank managements on services being offered to credit card holders. Key words: Bank credit cards. Visa, Master card, Amex, American express, Juristic resolution, Fatwas International Islamic juristic assembly.

Autonomous Ration Shops Using Database Management System and Embedded System

This paper centres around structure and execution of Automation of Ration Shop. In ongoing situation, all general society and private parts go for computerization in their procedure. Common Supplies Corporation is the significant open segment which oversees and conveys the basic items to all the residents. A portion of the restrictions of traditional proportion shop framework are because of manual estimations in the ordinary framework, consequently the client can not ready to get the precise amount of material. And furthermore there is an opportunity for the unlawful utilization of the items in the regular framework. for example the materials are taken by making incorrectly sections in the register without the information on the apportion card holder. And furthermore the moderate preparing keeps a long line before the shop. To defeat these issues we go for the mechanization of the apportion shops. This article aims for the sequential recording of ration shop transactions to a database using a network of clients with a server. The paper involves a client side and server side. The client PC is the one which is in the ration shop and the server side contains the database and a PC. The client PC is connected with a weighing machine. The client module consists of arduino microcontroller, which is with the weighing machine. The customer with a ration card can have his allotted items and which will be updated to the server as he receives it. The weight of the item is recorded by the microcontroller based weighing machine to the PC. The customer can access the details of his purchase and the amount of items left in the shop through an ASP.NET based webpage. The server stores all the allotted items to a ration shop for each and every customer and also the total items allotted for the ration shop. This project aims in the minimization of ration related corruption including the black-market reselling of goods and also the incorrect weights of items supplied and price related issues.

AADHAAR ENABLED PAYMENT SYSTEM – A NEW INNOVATION TO DIGITAL PAYMENTS OF INDIA

Aadhaar enabled payment system (AEPS) is a type of payment system that is based on the unique identification number and allows Aadhaar card holder seamlessly make financial transaction through Aadhaar based authentication. The AEPS framework expects to enable all the areas of society by making monetary and banking administrations accessible to all the Aadhaar. AEPS is context through one can make fund transfer, make disbursement, make cash deposit, make extractions, make request for information about bank balance etc.

Design and development for detection and prevention of ATM skimming frauds

ATM Skimming is a major concern that needs to be addressed with a specific solution. ATM Skimming is done in two steps. One is stealing the Personal Information that is stored on the Debit card / Credit card using Rain cover connected to the card reader slot (ATM’s real card slot). The second is installing a Fake keypad that can capture the pin code when the card holder enters pin details. Few researchers have proposed solutions to address the issue using Image Processing techniques. However, it does not provide a complete solution in a long term. Hence it is of paramount importance to provide ATM with high security features. In order to solve the issue of ATM Skimming, An Embedded System design is proposed. The research is carried out in two phases. One is detection phase and the second is Prevention Phase. In the detection phase, Hardware components such as Arduino Mega, Force Sensing Resistor (FSR), GPS, GSM and Buzzer are used. Arduino Mega acts as a Central Processor that processes the information received from Force sensing resistor (FSR) and send SMS Messages to ROP and Bank Officials using GSM and informing them about the ATM Location using GPS where the Fraud is taking place. Buzzer can be used at the ATM Locations to alert nearby people. In the prevention Phase, as a preventive measure a Onetime password (OTP) technique is used. If a fraudster somehow succeeds in Fixing fake key pad and Rain Cover at ATM’s real card slot, When he tries to insert debit card, An OTP will be generated and is sent to the Card Holder which in turn he can know someone is trying to make Transactions and quickly he can ask bank officials to Block his account and inform ROP about the same. Expected findings of the proposed work is to detect Fake keypads and Fake card readers using FSR placed at the edges of Original Keypad and card reader slot. Sending messages to ROP, BANK OFFICIALS and CARD HOLDER using GSM. ATM locations are identified using GPS. Buzzers are used to alert nearby people.

The random forest algorithm for statistical learning

Random forests (Breiman, 2001, Machine Learning 45: 5–32) is a statistical- or machine-learning algorithm for prediction. In this article, we introduce a corresponding new command, rforest. We overview the random forest algorithm and illustrate its use with two examples: The first example is a classification problem that predicts whether a credit card holder will default on his or her debt. The second example is a regression problem that predicts the logscaled number of shares of online news articles. We conclude with a discussion that summarizes key points demonstrated in the examples.

Design of a Combination Tool

The undertaken project work involves design, analysis and manufacture of a COMBINATION TOOL to produce TABLE TOP NAME CARD HOLDER. The main advantage of this combination tool is it can be accommodated with different operations in one single stage. This will reduce the complexity of the design of the tool. As the number of stages increases the design complexity also increases. Therefore usage of this tool will reduces the manufacturing and the design complexity and make the things easy. The combination tool performs both cutting and non-cutting operations. It can be done in the following way- The piercing, notching, lancing & bending operations are performed in the first stage, and then the blank is kept in the inverted position in the second stage where another bending is carried out. The relative positions with the previously pierced holes are maintained during the bending operation, with locating pins.