Riskified, headquartered in Tel Aviv, helps businesses to realize the potential of eCommerce by making it safe, accessible, and frictionless. Their eponymous platform allows online merchants to create trusted relationships with their consumers. Leveraging machine learning that benefits from a global merchant network, the platform identifies the individual behind each online interaction, helping merchants eliminate risk and uncertainty.
N/A
TensorFlow
Score7.6 out of 10
N/A
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
Riskified is the perfect tool if your current set up is based in lots of manual review and high chargebacks rate. Once implemented it will inmediately increase the authorization rate as well as decrease the chargeback rate significantly. For a company that needs automated decision on blocking abusers it also makes sense, specially using the Policy protect returns and item limit modules.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
TensorFlow is great for most deep learning purposes. This is especially true in two domains: 1. Computer vision: image classification, object detection and image generation via generative adversarial networks 2. Natural language processing: text classification and generation. The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days). In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Collaboration; Riskified builds strong relationships with their clients and works to always meet the clients' needs
Ascend; This is a great way for Riskifieds clients to meet, collaborate and learn from each other
Innovations; Riskified puts a huge emphasis on listening to their clients and finding a way to meet their needs, whether it's chargeback related, fraud screening related or abuse related.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Missing functionality/ explanation: not having full understanding why some orders with multiple "red flags" are accepted/approved by Riskified
Missing functionality: It would be great if there was an option to resubmit an order after approving a second look (so that the customer doesn't have to place a second order)
The support I've received isn't always uniform (sometimes the agent will ask me to provide additional information about an order, sometimes they won't. It seems to be random?)
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. TR verified that a representative sample of customers was invited. More Info
Theano is perhaps a bit faster and eats up less memory than TensorFlow on a given GPU, perhaps due to element-wise ops. Tensorflow wins for multi-GPU and “compilation” time.
We are likely to renew our use of Riskified. Their solution has become a critical component of our fraud prevention strategy and day-to-day operations. The combination of increased approval rates, reduced chargeback risk, and operational efficiency has delivered consistent value. Additionally, their collaborative approach and alignment with our customer experience goals reinforce our confidence in continuing the partnership long term.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
It's very easy to use. When an interaction is declined, there's reasoning located on the right side of the screen. It's incredibly easy to use Single-Sign-On to log into the account, and explaining that to new team members is very easy. The process for adding new team members is easy and the FAQ's are very helpful.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
The account management is great and very responsive, but as previously mentioned, the company does not seem to be very proactive with spotting exiting integration issues or things that could be wrong from technical point of view. I would like to see Riskified doing more proactive integration monitoring and more regular technical reviews.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Community support for TensorFlow is great. There's a huge community that truly loves the platform and there are many examples of development in TensorFlow. Often, when a new good technique is published, there will be a TensorFlow implementation not long after. This makes it quick to ally the latest techniques from academia straight to production-grade systems. Tooling around TensorFlow is also good. TensorBoard has been such a useful tool, I can't imagine how hard it would be to debug a deep neural network gone wrong without TensorBoard.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
I would say that the main difference between Riskified and Signifyd is the level of client service, which drives success in other aspects. We did not have a dedicated account manager with Signifyd, so there was no one to deal with issues. Signifyd's billing is also very messy, and we found that they did not reimburse us for a significant amount of chargebacks. Riskified's billing is easy to reconcile, and we've never had that issue.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Keras is built on top of TensorFlow, but it is much simpler to use and more Python style friendly, so if you don't want to focus on too many details or control and not focus on some advanced features, Keras is one of the best options, but as far as if you want to dig into more, for sure TensorFlow is the right choice
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
Since implementing and working with Riskified we have seen a steady decrease in our fraud losses on our e-commerce orders. Riskified is able to quickly adjust its models to mitigate new trends
By eliminating the need to "challenge" orders we have been able to save on staffing needed for manual review and we have seen a decrease in callback rates for our fraud reviewed orders.
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info
