Recently, we held a live event where our team chatted with Simon, Neighbor’s senior manager of trust and safety. Neighbor allows homeowners to rent space they’re not using to individuals looking to store their personal property — in other words, “Airbnb for storage.”
During the discussion, Simon touched on key moments when fraudsters are likely to strike, Neighbor’s approach to fighting fraud, and more. We’ll summarize his insights below, but we recommend checking out the recording to get the most out of the discussion. Plus, you can see a demo of our new fraud investigation and link analysis tool, Graph, in the recording.
How Neighbor designed its platform to mitigate fraud
Trust and safety is super key to marketplaces, especially ones where online transactions turn into in-person transactions like Neighbor. “Making sure our users have confidence in the platform and trust that they're going to get what they came for is super important to the success of Neighbor,” Simon shared.
In particular, it’s vital for marketplaces to keep their users safe from fraud. Since its beginning, Neighbor has seen multiple types of fraud, including:
- Transaction fraud
- Money laundering
- Individuals signing up as both a host and renter, then paying for reservations with stolen credit cards to get money off the cards and into their own hands
- Fraudsters trying to appear as someone else
- Check scams
- False advertising
Fortunately, Neighbor has set up a number of fraud prevention measures. For example, while renters pay for their rental upfront, Neighbor holds onto the funds until the end of the rental period, at which point the host gets their payout. “This allows us to make sure these are legitimate transactions, it's not a stolen credit card, and that the host is actually providing the services they promised in their listing.”
In short, “being intentional and considering how you can approach these things to prevent fraud in the first place, just by the nature of how your product is designed, is vital.”
Building and scaling a trust and safety team for not only fraud prevention, but also resolution
Trust and safety isn’t a solo effort, and Neighbor quickly realized it’d need a full-on team as it scaled. “As you grow, you start to show up on people’s radars. If you have money, they're going to try and come for it.”
One important call-out Simon made is that trust and safety teams don’t just tackle fraud prevention, but also fraud resolution. “You need to be thinking about not just how you're going to try and prevent fraud, but also what you're going to do when it slips through your cracks — because it will. This is where having a great team comes into play. It's not just about building fences and walls around your product. It's also about who's on the other side that's going to deal with something when it gets through.”
“Empowering those people to be able to take care of and resolve issues as they come up is the key to success, especially if you're a startup and can't get all the nicest, neatest toys for combating fraud. People, at the end of the day, create all value, and they will be the ones that will help you get through things when stuff does slip through the cracks.”
Moments when fraudsters are likely to strike
While fraud can strike at random, it can also be seasonal or a response to specific business events — specifically those that indicate growth, such as a funding or product announcement.
Neighbor experienced this first-hand after launching an aggressive referral program at the end of 2021. “Holidays tend to be a slower period, so we wanted to try and do something to maintain growth through the slow season. Our referral program is typically about $50 for both parties if you successfully refer a friend, and we ramped that up to $300 each,” shared Simon.
“We knew people would come for that, so we tried to prep for it, but we were actually really surprised by the fraud effort that came in to try and abuse this program. We had some 300 accounts created over roughly 24 hours trying to get in through our referral program, which was surprising for us. We weren't quite prepared for that level of effort from fraudsters against us."
On manually investigating fraud
Simon’s general fraud mindset is that it’s inevitable, so you need to have the right processes and people in place to deal with it. “Fraud is ever-evolving and ever-present. It's really about being intentional with your planning and expecting fraud to happen. If it's not a big deal, you'll be pleasantly surprised. And if it is a big deal, you'll be there to catch it.”
As such, Neighbor was prepared to handle the influx of fraud that came with its holiday referral campaign. “We knew people would likely try to take advantage, so we set up a manual process for reviewing these payouts. While we definitely saw a significantly higher amount of fraud than we were expecting, we already had the processes in place to deal with it. It was pretty tedious, but it ended up really saving us in this instance.”
That said, Simon acknowledged that their process wasn’t perfect. “It was a really tedious process to go in and review. We got lucky in the fact that these fraudsters were overly formulaic in how they approached it, so they were actually pretty easy to identify and we did not pay out anyone other than confirmed successful customers, which was really nice.”
“But we definitely learned that there's a balance between effort and protection. And if I could go back, I definitely would introduce more automated systems.”
One of the reasons finding and removing fraud clusters was so tricky and manual for Neighbor is because databases aren’t typically built with trust and safety in mind. “So we really had to dig into our data to try and find those indicators for collusion, which was a lot of manual ad hoc SQL queries into the databases, looking for things like IP address, device IDs — things that we had, but gaining access to see those and the connections was really complicated. So it was pretty tedious and complicated to go and do these investigations.”
How Neighbor uses Graph, Persona’s link analysis tool, to fight fraud
Fortunately, Neighbor has since been able to streamline its investigation process and proactively fight fraud with Persona’s new link analysis tool, Graph.
“Linking systems like Graph are so important. We wanted something like this very badly, and we were already using Persona's ID verification processes, so when they showed us the tool, I immediately said, ‘Yep, I want that. That's something we need’ It was obvious this is something we needed, especially in the stage we're in, to just really hone in on these organized group attacks against our site and to be able to identify them and tackle them quickly. So it was a pretty easy sell.”
And Simon wasn’t the only one who was impressed. “There were some jaws-on-the-floor kind of reactions when we saw how it would work because getting this kind of linking information has been so tedious for us, and Graph’s interface is so beautiful, easy, intuitive, and even kind of enjoyable to use. So my team was ecstatic.”
Since implementing Graph, Neighbor has seen immediate benefits. “Graph has cut through a lot of those issues we discussed, especially in the sense of quickly identifying if this is a problematic group of individuals or just a single lone wolf bad actor. We can find common threads of IP, device ID, address, phone number, verification documentation, and government IDs, and quickly figure out what we're dealing with without a lot of in-depth effort or pulling in another team."
“So it really gives my team the ability to identify the various levels of fraud and issues that we're seeing and determine quickly what we need to do to deal with this, which has been phenomenal — much better than having to write a new SQL query every time something comes up, bug an analytics person to get us the data, and bug an engineer to see if they know how something works. It cuts through all of that, keeps it on my team, and makes it quick.”
In fact, Graph frees up so much time that Simon now tells other teams to report any weird behavior on the site. “Graph lets me make my team available to the rest of the company. We can tell everyone, ‘If you see something weird, ping trust and safety’ and my team can take that information, plug it into Graph, and go, ‘oh hey, this bad actor is linked to a lot of other accounts. Clearly, this is organized behavior, and we're dealing with some kind of fraud ring here.’
“So it really gets us from, ‘hey, I've noticed a problem’ to doing something about it really quickly regardless of where the fraud is coming in or how it's being noticed."
Convincing executive teams to care about safety by design
Simon ended by giving two pieces of advice on how to convince executives to care about trust and safety: coming in with data and being good at storytelling.
- Make sure you have numbers and anecdotal evidence of the problem not caring about trust and safety is going to create.
- Think about whether this is a lethal or costly mistake for the business, because if it isn't, it probably isn't as important to your business, especially if you are in the early stages of growth.
If they’re still not convinced or decide to double down on other priorities, Simon says you may need to sit back and bide your time. “You might need to wait until a problem occurs and be ready to go, ‘Hey, here's a good example of what I've been talking about. Let's chat about how we don't have this happen again.’”
Interested in learning more about building trust and safety programs to mitigate and fight fraud? Watch the full discussion.