#11 - 1 Hour in Excel = 3 Weeks Head Start on Fraudsters

Anyone that has dabbled in fraud prevention knows the first KPI to look at: Chargeback Rate.

But at the same time, we all know the truth:

It’s mostly a meaningless metric.

At least for day-to-day operations.

The reason is simple: Chargebacks are a lagging indicator, and usually take weeks to mature.

This means that if you’re relying on chargebacks to tell you something’s cooking, you’re weeks behind the fraudsters attacking you.

There are plenty of ways to get leading indicators for fraud. Or at least less-lagging ones.

You can implement chargeback alerts (i.e., Ethoca & Verifi), you can link known chargebacks to yet-to-mature chargebacks, and you can even sample your flow with manual review.

But all of these methods take time, resources and money.

Here’s the thing: there is a way to easily establish some monitoring tools that would help a lot.

So building upon ​the basic KPIs you want to monitor, today we’ll deep dive into tracking loss maturation.

Tracking loss maturation will build clarity, confidence and control within your business.

It helps you make better sense of the flow of incoming chargeback notifications, and build a clearer picture of your business health.

Worried you might be under attack? You’ll spot it MUCH earlier.

Want to know if the changes you implemented in your setup stopped it? You don’t need to wait for months.

Want to forecast losses for your budget planning? You will be more accurate.

Here’s how:

Method A - loss maturation heat maps

You’re already tracking your chargeback rates.

Side note: we’re tracking it by payment origination date, not chargeback receipt date.

Now make the following changes to the new metric:

  1. Track it on a calendar week basis

  2. Track all weekly cohorts in the same chart (up to 12 cohorts - or weeks - should be enough)

  3. Apply a heat map to easily spot patterns.

Here’s an example:

Pro tip: Excel’s conditional formatting will do that with a couple of mouse clicks.

Let’s break-down what we see above. Not the artifact itself, but its implications:

We see a fraud attack hitting this particular flow during CW 38-40.

Notice how we can spot it already 2-3 weeks into an attack?

Not only do you get a quick alert that something is going on, but you also know exactly when it started.

Then it looks like on CW 40 some strategy changes have been applied to stop the attack.

You can notice the difference almost immediately, and within 2 weeks you know you’re in the clear.

This gives leadership the confidence you are in control, DESPITE the fact you still get overflowed with chargebacks from the previous weeks.

To multiply this effect, implement this over different segments to reach better granularity.

This can be implemented over:

  • Sellers

  • Regions/countries

  • Products

  • Etc.

Finally, just as a teaser - If you see a specific segment that trends towards early maturation as a default, this might mean you have a 1st-party fraud problem there.

Method B - loss maturation curves

Let’s talk about improving our loss forecast capabilities.

We already have the heat map above, and are tracking weekly loss maturation. But how can we forecast future losses with it?

What is missing is analyzing our business’ general loss maturation. Meaning, how losses mature into chargebacks over time.

This is an easy exercise - just run the calculation from method A on your historical data.

Here’s an example:

Let’s break it down:

Looking at a sufficiently old dataset (>6 months), we measure how much of the chargebacks arrived at which point in time.

We can see a fluctuation in the first few months as the business’ flow composition changed, but you can also see how it settled in the last four months:

About 45% of chargebacks mature after 4 weeks. About 80% after 8 weeks, and about 90% after 12 weeks.

Side note: These numbers might look differently in your specific business, but they match overall industry standards.

Combining this general maturation pattern with your weekly cohort heatmaps will tell you how much losses to budget for with greater accuracy.

To conclude:

Analyzing and tracking loss maturation patterns is the single most effective tool a business has for creating clarity and confidence.

It’s as easy as running a query and porting the results into an excel sheet.

By spending 1-hour a week, your team now knows what’s happening and how their actions are impacting fraud.

And it keeps your finance team happy, now that their forecasts are finally aligned with the reported PnL.

Unfortunately, my experience shows that tracking loss maturation is also criminally underutilized.

Why? I don’t know.

Maybe some teams prefer the chaos and anxiety of not knowing what’s going on.

Or maybe they prefer to pay $35 per chargeback alert and call it a day.

But imagine the power of combining your alerts into such a system. Being able to measure how much of your expected losses are actually maturing into chargebacks.

Chargeback alerts are great. But they are even better when they feed into a system that aims to sort data into insights.

Have questions or feedback? Reply to this email, I read all messages.

That’s all for this week.

See you next Saturday.

P.S. If you feel like you're running out of time and need some expert advice with getting your fraud strategy on track, here's how I can help you:

Fraud Strategy "Power Call" - Book a consultation call with me to get clear, actionable recommendations that fit your budget. Guaranteed.
​Book a Call Now >>​

Fraud Strategy Workshop - are you an early-stage Fintech that needs to move fast and with confidence? Book this 1.5-hours workshop to get instant insight into your vulnerabilities, optimization opportunities, and get clear actionable recommendations that won't burn through your budget.
Book Your Workshop Now >>​

Fraud Strategy Transformation Program - are you a growth-stage Fintech in need for performance optimization or expansion of your products offering? Sign up to this 6-8 weeks program, culminating in a tailored made, high-ROI roadmap that will unlock world-class performance.
Schedule a Call Now >>

 

Enjoyed this and want to read more? Sign up to my newsletter to get fresh, practical insights weekly!

Previous
Previous

#12 - Why fraud beats your KYC (and how to fix it)

Next
Next

#10 - Build vs Buy: When DIYing Fraud Tech Makes Sense