Online merchants are expected to provide a pleasant purchase experience for their customers, but might unintentionally offer an open door to fraudsters. The challenge is clear; how can an online merchant provide his customers with the smoothest shopping experience without exposing himself to high financial losses due to fraud?
While a credit approval process is mostly like reduced to the snapshot with credit checks, day-to-day business needs additional instruments. Tools for continuously monitoring online banking transactions as well as internal activities is a must-have to protect both, the customers and banks.
Banks and financial institutions utilize credit checks provided by data-quality businesses. Traditionally the result of a credit check is a scoring model based on single-item decisions reflecting static information. Unfortunately, static information matures and can lead to inappropriate conclusions. The challenge is; how can such businesses turn static data into a dynamical scoring over time?
Spotting to marketplaces, they experience the same issues as retailers but additionally also in dealing with new merchants in the onboarding phase. Initial due diligence might be a good indicator but is no guarantee that the new retailer will add value to the marketplace. The challenge is; how can a marketplace distinguish between the good participants and the bad ones?
Let us simplify it to the basics. Assume that something evil hits your business on a transactional level or end customer level. The approach is to know, by always asking the questions such as “what is abnormal?”, “what is different?” or “not as always?”. The advantage is that these fundamental questions allow extending the logic in as many dimensions as needed to find relevant patterns, behaviors and of course, the anomalies causing the evil attacking the business.
The starting point of such tools is to select and combine any criteria of the data pool and to describe based on rules what is regular and what could be a potentially irregular activity. In other words, it is to define the expected behavior based on historical experience and then let the logic analyze the actual values or transactions against the predefined nominal behavior.
To help merchants to combine static, single-item based decisions with dynamic customer profiling including their behavior over time DIMOCO developed RFO, the high-efficient risk, fraud & optimization engine. We protect merchants with a customized risk management system. Intelligent algorithms identify customers, compare and score behavior patterns and monitor all individual transactions. We also identified a demand for companies outside the payment and financial industry, to make use of a rule-based risk- and fraud-detection tool.
Curious about how RFO can protect you from financial losses and how its advanced functionalities can give you more insights about your business?