Get Ready for the Holiday Rush: A Toolkit for Sift Science Customers
By Sarah Beldo /
2 Oct 2017
It’s the most wonderful time of the year…for fraudsters! Last year, e-commerce fraud spiked by over 30% during the holidays. That means about 1 in every 97 transactions was fraudulent. And fraudsters are upping their game every year, even offering online courses for criminals looking to make a quick buck during the cooler months. Fortunately, though, you have a powerful ally in your corner: Sift Science.
To set the stage, let’s start with some quick facts about online shopping trends during the holidays:
- Online holiday retail spending is projected to grow by 12% this year, with consumers spending 8% more than they did last year (Forrester).
- Browsing starts early! More than half of U.S. holiday shoppers start planning their gifts in October or earlier, the NRF found.
- Big crowds gather on big days. Cyber Monday was the busiest U.S. shopping day of holiday season 2016, according to ComScore. November 29 (the day after Cyber Monday) and November 25 (Black Friday) took the second and third spots.
- This year, Salesforce predicts that 50% of online holiday shopping will be wrapped up by December 3.
- Fraudsters operate on a global scale. LexisNexis conducted a study that found international ecommerce fraud happens more than twice as frequently as domestic ecommerce fraud.
Here’s how Sift Science can empower you to protect your business during this season.
Make sure your team is up to speed on using the Sift Science console
Sift Science is a one-stop-shop for all your fraud-fighting needs, as long as your team knows how to use the console! Have your team brush up by looking over our support docs – and be sure to include any contractors or temporary staff you’re hiring to support the holiday rush.
Need the basics? Check out our popular Everything You Wanted to Know About Sift Science webinar, or peruse our Getting Started with Using Sift Science guide. And make sure your fraud fighters know about our support team, who are here to help during the holiday season and beyond.
Start automating (if you haven’t already)
The holiday rush is no joke. For businesses with smaller fraud teams, fraud-fighting during this busy shopping period can be overwhelming, and lots of businesses bring in extra temporary help. Even large teams can find themselves drowning in manual review before too long.
When the orders start flowing in, you’ll be glad you set up some automation thresholds for blocking and accepting orders. Harness the power of Workflows to build and manage your fraud logic before you’re pressed for time; for a deep dive on Workflows, check out this helpful blog post. But if you do want to maintain the flexibility to engage in some manual review, never fear: you can always create review queues to allow a fraud analyst to dig in.
Watch a webinar on how to get up and running with our automation tools, Workflows and Decisions.
Adjust your automation thresholds
During the holidays, the number of transactions and the average transaction value is likely to increase. You’ll need to update your fraud logic accordingly! Consider adjusting thresholds so that the manual review rate remains the same. That might mean accepting or blocking more orders, depending on your tolerance for risk and review. Think it through before the holidays; you won’t have time to think it through during!
One fraud expert recommends that you find a core 2-3 indicators of good buyers, then make those fundamental to the manual review process. When your team sees these indicators, accept the order without further analysis. Further analysis will confuse the auditor and increase the chance of making the incorrect decision (most people are risk averse and don’t want to process a potentially bad order). Also, create firm caps as to how long a team should review orders for.
Clear up any integration errors
Sift Science relies on your data to detect fraudsters. That’s why it’s so important for you to have the best integration possible. Make sure you clear up any integration errors before the holidays so we can help you fight fraud accurately and efficiently.
Not sure whether you have any errors? Check out the Integration Health page via the Developer tab on the Sift Science console. If you’re a bit rusty, here’s a quick refresher. The page is divided into four parts: Integration Overview lets you assess the number of errors we’ve seen over a given period of time; Volume Overview shows you how well integration components are performing; Errors Overview lets you manage and prioritize issues that are impacting integration; and Activity Overview allows you to review integration holistically.
For more on how you can use the Integration Health page to help you clear up errors, check out this blog post.
Integrate our mobile SDK
Last holiday season, half of web traffic and 30% of retail sales came from mobile sites, according to Adobe. And although mobile payments are expected to account for 70% of global revenue by the end of this year, most businesses don’t have a system in place to detect and respond to mobile fraud. Are you prepared for mobile shoppers?
Take steps to protect your customers and your bottom line by downloading Sift Science’s mobile fraud detection SDKs. Although Sift Science protects your mobile orders as long as you’re sending backend events, installing the SDK will supplement your integration by providing even richer information about how people interact with your mobile app. For example: who’s the mobile carrier? What’s the device and app version? How may users are sharing the same device ID? After integrating the mobile SDK, Sift Science customers often find that mobile-related signals are some of the strongest contributors to their machine learning model.