Best Practices for Manual Fraud Reviews

For many merchants, manual fraud reviews are essential to reducing fraud. At the same time, those reviews can be time-consuming and burdensome. Not to mention, even after reviewing hundreds of orders, you may still have a fraud problem.

So how do you make sure you’re getting the most benefit from manual fraud reviews? We’ve outlined our top tips to help you.

What are Manual Fraud Reviews?

Manual fraud reviews are exactly like they sound — fraud specialists manually review orders and transaction data to determine if an interaction is fraudulent or not. The manual fraud review is a fraud prevention method that many businesses use.

Some businesses use machine learning algorithms — or coded rules — to first filter information from the interaction. If the algorithms can’t give a definitive decision, those transactions are usually flagged and sent to the manual review team.

How Do Manual Reviews Work?

Typically, fraud reviews are done by a dedicated fraud specialist or data analyst. This person will evaluate all available data and then make a decision. It sounds simple enough. However, the manual fraud review process can be long and tedious.

A manual fraud review usually includes the following steps.

1. Evaluate incoming data.

A fraud specialist will first identify high-risk interactions, then analyze all available data — such as credit cards and other payment information, phone numbers, addresses, customer account information, and more. The specialist will review the data for accuracy, compare it to historical data, verify the customer information, look for suspicious emails, and more.

2. Contact customers.

Sometimes, the specialist may have to manually contact customers to validate their information. This may include a call, an email, or a text.

3. Examine past disputes.

If a customer has disputed a transaction in the past, the specialist will have to review the details of that past dispute to make an informed decision.

4. Make a decision.

Based on the analysis, the specialist will have to make the decision to accept or deny the customer’s transaction.

5 Tips for Improving Your Fraud Review Process

Some companies completely eradicate manual reviews — but only because their industry demands it. Quick service restaurants, for example, can’t afford the time it takes to do manual reviews.

However, that doesn’t mean every business should eliminate their manual review process. The problem is some businesses might rely too heavily on manual reviews.

If you’re still in the business of conducting your own fraud reviews, here are five strategies for making that process smoother and more efficient.

1. Create a fraud review team that meets your business needs.

When setting up your fraud team, make sure you have the right number of people so you can allocate their time appropriately. Each business is different, so your needs may not be the same as another business in your industry.

For example, say an ecommerce merchant processes 10,000 orders per month. And out of those orders, 1,000 to 2,000 need to be manually reviewed. For one team member whose sole responsibility is fraud, that averages out to be 50 manual reviews per day.

Also keep in mind that around holidays or peak busy times, you might need two or three employees to manually review interactions. Because too many reviews and too few agents can negatively impact a customer’s lifetime value. For example, a team tasked with too many reviews may falsely decline good orders — increasing your false positive rate — just to keep up. And many shoppers won’t return to a website that declines their order.

2. Organize your data.

Another way to improve your review process is by making transaction data and customer information easy to access. If your fraud team knows what to look for and exactly where to find it, the process can go a lot quicker.

Proper data management includes using a customer relationship management (CRM) platform, cleaning and validating your data, segmenting customer data, and setting up policies for data handling.

3. Evaluate the cost of manual reviews.

Depending on the type of interaction, the average cost of a fraud review is between $2 and $5 each. That includes payroll, taxes, and overhead expenses.

The number of orders you review will depend on your business’s order volume. So, if you process 10,000 orders and review 1,000 of them, you’ll spend about $5,000 a month on manual reviews.

The point of reviewing your monthly expense on manual reviews is to ensure you’re using your resources and money wisely. Manual reviews should save you money. But if you’re spending more to review orders than you’d lose if all those orders were fraudulent, then you’re wasting money. Many businesses focus so heavily on allocating resources to fighting fraud that they miss out on opportunities to grow the business.

4. Measure your review-then-decline rate.

You also want to make sure you’re doing the right amount of fraud reviews — which you can determine by measuring your company’s review-then-decline rate. To calculate your review-then-decline rate, divide the total number of orders your agents declined for fraud by the total number of manual reviews done by your agents.

Your ideal review-then-decline rate should be between 30% and 60%. If your review-then-decline rate is less than 10%, then you unnecessarily reviewed more than 90% of the transactions you reviewed.

So if you marked 100 orders for fraud review, you could have outright approved more than 90 of them, which would have eliminated unnecessary friction and reduced operational costs.

However, if your review-then-decline rate is too high, that means you’re spending a lot of time reviewing orders you could have just declined. Moreover, declining those orders outright would have reduced the operational costs of manual fraud reviews.

5. Combine manual reviews with fraud technology.

Technology can truly elevate your manual review process — helping you accomplish more in less time. Imagine what your business would look like if you could reduce your order decline rate, accept more good orders, improve internal processes, and create a more balanced workload for your fraud teams.

A fraud prevention solution can help you replace manual labor with an automated process. For example, it can collect and analyze your data in seconds — way faster than any human can. Secondly, because fraud software is an automated system, it never gets tired, unlike your employees. It works around the clock, so even when your employees are done for the day, your business is still protected.

The best part is that you don’t have to completely replace manual reviews with technology if you don’t want to. Technology just makes the process more efficient and accurate. Take a look at this case study with Jeffers Pet, for example. Implementing a solution drastically reduced the amount of time they spent on manual reviews and reduced the total amount by 90%.

Want to Improve Your Fraud Management Strategy?

If you’ve determined it’s time to take another look at your risk management strategy, but you don’t know where to start, consider reaching out to a fraud specialist. There are fraud providers — like Kount — that can help you decide the best course of action to take towards reducing fraud risks.

To learn more about fraud detection and how automated tools could help you, check out our technology.