Tag: Decisioning
If you’re looking to buy new decisioning software, your first inclination might be to issue an RFI or an RFP. However, that may not be the best idea.
Time is the only resource we can’t get more of, which is why we obsess over saving it. Over the last several years, a new time saver has emerged – APIs.
Our Attribute Toolbox provides maximum flexibility and multiple data sources you can use in the calculation and management of attributes.
Digital transformation is the new business model, and its powered by data and the insights gleaned from data.
The 2019 report reveals new consumer and lending insights, an overview of the regulatory landscape, and what's next for machine learning and alt data.
You want to use big data, but how do you make your analytics truly actionable to stay ahead of the competition? Using an analytical sandbox is the answer.
There are a lot of people talking about big data who are not fully leveraging the value of their data. How do you use data to innovate and stay competitive?
Once a scorecard has been redeveloped, it is important to measure the impact of changes within the strategy by replacing the old model with the new one. This impact assessment can be completed with a swap set analysis.
With 81% of Americans having a social media profile, you may wonder if social media insights can be used to assess credit risk. When considering social media data as it pertains to financial decisions, there are 3 key concerns to consider.
Later this year, FICO will retire its Score V1, making it mandatory for those lenders still using the old software to find another solution.
Key drivers to auto financial services are speed and precision. What model year is your decisioning system? In the auto world the twin engineering goals are performance and durability. Some memorable quotes have been offered about the results of all that complex engineering. And some not so complex observations. The world of racing has offered some best examples of the latter. Here’s a memorable one: “There’s no secret. You just press the accelerator to the floor and steer left. – Bill Vukovich When considering an effective auto financial services relationship one quickly comes to the conclusion that the 2 key drivers of an improved booking rate is the speed of the decision to the consumer/dealer and the precision of that decision – both the ‘yes/no’ and the ‘at what rate’. In the ‘good old days’ a lender relied upon his dealer relationship and a crew of experienced underwriters to quickly respond to a sales opportunities. Well, these days dealers will jump to the service provider that delivers the most happy customers. But, for all too many lenders some automated decisioning is leveraged but it is not uncommon to still see a significantly large ‘grey area’ of decisions that falls to the experienced underwriter. And that service model is a failure of speed and precision. You may make the decision to approve but your competition came in with a better price at the same time. His application got booked. Your decision and the cost incurred was left in the dust – bin. High on the list of solutions to this business issue is an improved use of available data and decisioning solutions. Too many lenders still underutilize available analytics and automated decisions to deliver an improved booking rate. Is your system last year’s model? Does your current underwriting system fully leverage available third party data to reduce delays due to fraud flags. Is your ability to pay component reliant upon a complex application or follow-up requests for additional information to the consumer? Does your management information reporting provide details to the incidence and disposition of all exception processes? Are you able to implement newer analytics and/or policy modifications in hours or days versus sitting in the IT queue for weeks or months? Can you modify policies to align with new dealer demographics and risk factors? The new model is in and Experian® is ready to help you give it a ride. Purchase auto credit data now.
As Big Data becomes the norm in the credit industry and others, the seemingly non-stop efforts to accumulate more and more data leads me to ask the question - when is Big Data too much data? The answer doesn’t lie in the quantity of data itself, but rather in the application of it – Big Data is too much data when you can’t use it to make better decisions. So what do I mean by a better decision? From any number of perspectives, the answer to that question will vary. From the viewpoint of a marketer, maybe that decision is about whether new data will result in better response rates through improved segmentation. From a lender perspective, that decision might be about whether a borrower will repay a loan or the right interest rate to charge the borrower. That is one the points of the hype around Big Data – it is helping companies and individuals in all sorts of situations make better decisions – but regardless of the application, it appears that the science of Big Data must not just be based on an assumption that more data will always lead to better decisions, but that more data can lead to better decisions – if it is also the “right data”. Then how does one know when another new data source is helping? It’s not obvious that additional data won’t help make a better decision. It takes an expert to understand not only the data employed, but ultimately the use of the data in the decision-making process. It takes expertise that is not found just anywhere. At Experian, one of our core capabilities is based on the ability to distinguish between data that is predictive and can help our clients make better decisions, and that which is noise and is not helpful to our clients. Our scores and models, whether they be used for prospecting new customers, measuring risk in offering new credit, or determining how to best collect on an outstanding receivable, are all designed to optimize the decision making process. Learn more about our big data capabilities
In today's data driven world, decisioning strategies can no longer be one-dimensional and only risk-focused. By employing a multidimensional decisioning approach, companies can deliver the products and services customers need and want.
When we think about fraud prevention, naturally we think about mininizing fraud at application. We want to ensure that the identities used in the application truly belong to the person who applies for credit, and not from some stolen identities. But the reality is that some fraudsters do successfully get through the defense at application. In fact, according to Javelin’s 2011 Identity Fraud Survey Report, 2.5 million accounts were opened fraudulently using stolen identities in 2010, costing lenders and consumers $17 billion. And these numbers do not even include other existing account fraud like account takeover and impersonation (limited misusing of account like credit/debit card and balance transfer, etc.). This type of existing account fraud affected 5.5 million accounts in 2010, costing another $20 billion. So although it may seem like a no brainer, it’s worth emphasizing that we need to continue to detect fraud for new and established accounts. Existing account fraud is unlikely to go away any time soon. Lending activities have changed significantly in the last couple of years. Origination rate in 2010 is still less than half of the volume in 2008, and booked accounts become riskier. In this type of environment, when regular consumers are having hard time getting new credits, fraudsters are also having hard time getting credit. So naturally they will switch their focus to something more profitable like account takeover. Does your organization have appropriate tools and decisioning strategy to fight against existing account fraud?
By: Andrew Gulledge I hate this question. There are several reasons why the concept of an “average fraud rate” is elusive at best, and meaningless or misleading at worst. Natural fraud rate versus strategy fraud rate The natural fraud rate is the number of fraudulent attempts divided by overall attempts in a given period. Many companies don’t know their natural fraud rate, simply because in order to measure it accurately, you need to let every single customer pass authentication regardless of fraud risk. And most folks aren’t willing to take that kind of fraud exposure for the sake of empirical purity. What most people do see, however, is their strategy fraud rate—that is, the fraud rate of approved customers after using some fraud prevention strategy. Obviously, if your fraud model offers any fraud detection at all, then your strategy fraud rate will be somewhat lower than your natural fraud rate. And since there are as many fraud prevention strategies as the day is long, the concept of an “average fraud rate” breaks down somewhat. How do you count frauds? You can count frauds in terms of dollar loss or raw units. A dollar-based approach might be more appropriate when estimating the ROI of your overall authentication strategy. A unit-based approach might be more appropriate when considering the impact on victimized consumers, and the subsequent impact on your brand. If using the unit-based approach, you can count frauds in terms of raw transactions or unique consumers. If one fraudster is able to get through your risk management strategy by coming through the system five times, then the consumer-based fraud rate might be more appropriate. In this example a transaction-based fraud rate would overrepresent this fraudster by a factor of five. Any fraud models based on solely transactional fraud tags would thus be biased towards the fraudsters that game the system through repeat usage. Clearly, however, different folks count frauds differently. Therefore, the concept of an “average fraud rate” breaks down further, simply based on what makes up the numerator and the denominator. Different industries. Different populations. Different uses. Our authentication tools are used by companies from various industries. Would you expect the fraud rate of a utility company to be comparable to that of a money transfer business? What about online lending versus DDA account opening? Furthermore, different companies use different fraud prevention strategies with different risk buckets within their own portfolios. One company might put every customer at account opening through a knowledge based authentication session, while another might only bother asking the riskier customers a set of out of wallet questions. Some companies use authentication tools in the middle of the customer lifecycle, while others employ fraud detection strategies at account opening only. All of these permutations further complicate the notion of an “average fraud rate.” Different decisioning strategies Companies use an array of basic strategies governing their overall approach to fraud prevention. Some people hard decline while others refer to a manual review queue. Some people use a behind-the-scenes fraud risk score; others use knowledge based authentication questions; plenty of people use both. Some people use decision overrides that will auto-fail a transaction when certain conditions are met. Some people use question weighting, use limits, and session timeout thresholds. Some people use all of the out of wallet questions; others use only a handful. There is a near infinite possibility of configuration settings even for the same authentication tools from the same vendors, which further muddies the waters in regards to an “average fraud rate.” My next post will beat this thing to death a bit more.