CreditStar is a web application that provides a platform for banks and other credit-issuing organizations to predict the credit risk associated with individual credit card applications. An algorithm exists to predict, based on specific financial information, the probability of a client to default in payment of a credit card loan or not; and advice the organization on the best credit offer to make.
The team for this project comprised of 3 UI/UX designers, a Data Scientist, and a Software Engineer.
The objective of this project was to create an accessible and functional application that predicts if a credit card applicant would default in his/her payment or not.
Default implies failing to make payment on a debt by the due date. According to Investopedia, a default occurs when a borrower is unable to make, misses, avoids, or stops payments. A Default can occur on secured debts such as Mortgage loans or on Unsecured debts such as Student loans or Credit cards.
Most times, financial institutions are at the receiving end of default in credit card payment, suffering huge losses - the reason being that there is no asset that backs the debt. Financial institutions need to protect themselves against such defaulters.
The demography of our research was centered on individuals from the banking industry including Bankers and Financial Analysts, with significant working experience who have, at one point or the other faced the problem we are trying to solve.
https://lh4.googleusercontent.com/qrP84kFla8Mn2p9TUGGR5tPMX68qbguVG-6ttfcWuQ0B26f1XGW7KsYwRR0XWCbouu4NuRNcBPy-vykw7YRW6f5vvoR4EKXFga57T6hI0BDuHALjMdIQRNAExcMA4puOGTwzxi0-
From our research, we were able to deduce the following:
https://lh5.googleusercontent.com/UPt0Tkz9b6RchzhwPAjk-tHeRfUXdjbNknEITf9CLSS6IPCLqu6RftiDXQ0Jp-wueoBeCozwsGX25WCcL7AkLNIbcTcb7UmI_RgbgVsgDj2ttfAPA7kBXNMZPcRapWWRZXNMCZxY