Best Practices for Achieving Success with Custom Modeling and Machine Learning

One of the most common reasons organizations fail to realize significant improvements in risk management after implementing custom modeling solutions can be described with one phrase: Junk in. Junk out. This article discusses best practices as it relates to data management and other factors that are shown to improve performance when it comes to custom modeling and machine learning or artificial intelligence.

It’s not just breadth of data, but also quality of data, that is important. One of the biggest misconceptions about machine learning (ML) and artificial intelligence (AI) is that you can just flip a switch and let the technology work its magic.

Read More

Processing Through Acquirers with Lower Fraud Rates Reduces the Need for SCA Under PSD2

Many merchants both within and outside of Europe are concerned with meeting Strong Consumer Authentication (SCA) requirements and how this might impact sales when nearly every eCommerce order over €30 will require two-factor authentication. A lesser known fact is that this order value threshold for requiring SCA increases in multiple tiers based on the fraud rates of both the acquiring and card issuing banks facilitating the transaction, suddenly making the fraud rates of a merchant’s European processors much more important.

Read More

Klarna Becomes Largest Private FinTech Company in Europe Following $460 Million Funding Round

Klarna, a payment company offering micro credit for online transactions like PayPal Credit, serves consumers and merchants in Europe and the United States while preparing to launch in Australia and New Zealand. They recently announced an equity funding round raising $460 million, valuing the credit terms alternative payment provider at $5.5 billion.

The number of Klarna users in the U.S. is growing by 6 million per year.

Read More

New Fraud Practice White Paper Discusses Techniques and Benefits Related to Identifying Low Risk Customers and Applicants

A new white paper from The Fraud Practice titled “Identifying and Streamlining Low Risk Customers or Applicants: Techniques and Benefits” is now available. This free white paper discusses the application of technology and techniques to derive signals of low or reduced risk and the benefits of identifying such orders in terms of conversion and screening costs when low risk orders or applicants can be streamlined or fast-tracked.

Identify Low Risk White Paper

Request your copy of this free white paper

Cyber Monday and Black Friday Reach Record Highs Totaling More Than $14 Billion in Online Sales

Cyber Monday 2018 was the largest online shopping day recorded in the U.S. with $7.9 billion in sales volume, according to Adobe Analytics. Online sales on Black Friday grew 24 percent from 2017 to $6.2 billion this year as mobile shopping and pick-up in-store saw the largest growth.

While Cyber Monday online spending increased about 20 percent year-over-year, mobile payment transactions represented $2.2 billion of the $7.9 billion sales total for the day. Mobile spending was up nearly 56 percent from Cyber Monday 2017. Adobe additionally estimates that online sales on Thanksgiving Day reached $3.7 billion, an increase of 29 percent from 2017.

Read More

Consumers More Concerned with Fraud than Overspending During Holiday Season

A recent survey from CaptialOne found that 26 percent of consumers believe Cyber Monday is the riskiest day of the year to shop online while 85 percent of US consumers believe the risk of identity fraud is elevated during the holidays. Financial fraud was the top concern amongst Americans, surpassing consumers who were most concerned about potentially overspending during the holiday season.

Read More

Alibaba’s Singles Day Sales Exceed US Online Sales from Thanksgiving Through Cyber Monday

Alibaba, China’s largest online company, reported gross merchandise value (GMV) of $30.8 billing on Singles Day or 11/11. This metric, which represents the dollar value of goods sold by third parties over Alibaba’s platform, is up 22 percent from last year. Singles Day is the largest online shopping day in China, far exceeding the value of US online sales on Cyber Monday which reached a record $7.9 billion in 2018.

Read More

Measuring False Positives is Not an Exact Science but Using Multiple Metrics can Provide a Better Understanding

When a legitimate customer has their order declined because of fraud concerns they may purchase from a competitor and may never return to the merchant who turned them away. This is not only painful in terms of losing the sale and potentially the lifetime value of that customer, but this makes measuring false positives difficult. Even if an organization identifies customers who reattempt their transaction or call-in to customer service to complete their order, this is not a complete representation of the volume of sales insults; it may only be the tip of the iceberg.

The first step to effectively measuring false positives is understanding that it is not an exact science, that the metrics we can use are proxies, and the more methods we have for deriving and measuring these proxies the closer we can come to understanding the whole picture.

Read More

Nearly 90 Percent of U.S. eCommerce Sales are Domestic, Here are Several Reasons Why

A recent study from PPRO and Edgar, Dunn & Co. found that while about 40 percent of online sales in European countries are made to customers abroad, just 11 percent of U.S. eCommerce sales are purchases made from foreign countries. This lopsided figure underscores the difficulty of facilitating cross-border transactions, but there are many factors likely contributing to this large discrepancy.

Cross-border eCommerce is a two-way street, but traffic doesn’t flow evenly across the two directions. While just 11 percent of U.S. eCommerce sales originate outside of the United States, more than one-third of U.S. consumers shop online from brands and websites outside of the U.S. This is comparable to the share of consumers participating in cross-border eCommerce from Germany (32 percent) and the United Kingdom (38 percent).

Read More

Reports Show Merchants Struggle to Balance Fraud Prevention and Sales Conversion

Card Not Present channel Merchants cite order rejection rates of nearly 3 percent for domestic transactions and nearly 7 percent for international orders. Meanwhile more than half of merchants depend on AVS and CVV checks, considering them to be effective fraud tools. While most merchants measure fraud rates and order rejection rates, far fewer take the next step to understand false positives.

According to the Merchant Risk Council (MRC) 2017 Global Fraud Survey, eCommerce merchants declined 2.6 percent of all orders for suspected fraud, and 3.1 percent of orders over $100. CyberSource found higher order rejection rates in their 2017 Fraud Benchmark Study: 2.9 percent for domestic orders and 6.8 percent for international ones. While merchants are declining 3 percent of more of their orders, not all of these are actually fraud attempts.

Read More