We are moving fast towards a cashless society. Non-cash transactions reached 482.6 billion in 2016. Electronic wallets alone represented 41.8 billion. This massive amount of transactions makes this type of payment appealing for frauds. Indeed, for scammers and thieves, credit cards are a holy grail.
There are several types of credit card frauds. The most important one is the credit card not present fraud (CNP). Any purchase without the use of a merchant terminal or an ATM is a CNP purchase. CNP purchase amounts for 85% of all credit card frauds.
Banks rely on rule-based programmed systems to identify security breaches, resulting in 1% of the transactions being fraudulent.
Machine learning can provide a way to detect such CNP thefts to reduce this 1% of fraudulent transactions.
Online merchants, banks, credit card companies, credit reporting agencies, law enforcement agencies can benefit from the use of predictive modeling in credit card fraud detection. Stolen card information concerning minimal transactions is more likely to be unnoticed. Performing an automatic detection of such small fraudulent purchases is like looking for a needle in a haystack. It consists of identifying weak signals among a considerable quantity of genuine purchases. Even though the overall data handled by the financial industry are Big Data (transactions are usually in millions or even billions), fraudulent transactions, less than 1%, are Small Data.
Traditional machine learning tools work well with Big Data but do not perform well on a Small Data subset within a Big Data collection. Credit card fraud records are an imbalanced dataset where the actual data to identify and predict from is present in a minimal quantity among vast quantities of data. This small quantity of data hidden among numerous data is ‘weak signals.’
MyDataModels allows the financial industry to build Small Data predictive models automatically. No need for specific training. The input is your raw data. There is no need to normalize the data, handle outliers, or run feature engineering. MyDataModels provides for the seamless use of raw data. We obtained results from this specific dataset in a few clicks in less than 10 minutes on a standard laptop. Using TADA with this data set, a 99.78% accuracy of predicted fraudulent transactions was achieved.
MyDataModels brings a self-service solution for banking professionals who have Small Data to analyze and predictions to make.
According to a report published by Nilsen, in 2017, worldwide losses in card fraud reached $22.8 billion and is expected to reach $32.96 billion by 2021. In 2017 the medium consumer experienced an average loss of $429. 21% of credit card users suffered such a theft. Credit card theft results in substantial financial losses for the financial industry but also a breach of customer trust.
“The use of predictive models yields a sharp decrease in illegal transactions ”
By accurately predicting which transactions are likely to be fraudulent, credit reporting agencies, law enforcement agencies can significantly reduce illegal transactions. Online merchants, banks, and credit card companies can reduce substantially unauthorized transactions and provide credit card users an excellent customer experience.
Fraudulent activity is a high-cost threat with many consequences, including eventually hurting companies’ bottom line. The use of fraud detection analytics based on an automatic machine learning solution such as TADA empowers companies to identify these malicious activities right away and put a stop to them.