A Sigh of Relief: Learning How to Not Turn Away Legitimate Customers with Machine Learning and Data Science
Now imagine that you are the owner of a high-end fashion/jewelry eCommerce platform and you are told that you lost a legitimate customer that wanted to buy a $30,000 handbag, but she was turned away because of a legacy system that generated a false positive based on a simplistic review. Does it not make your heart hurt?
The good news is that there are an ever-improving array of tools available to you today to ensure that the occurrence of such a situation is minimized.
Our company recently worked with a firm that experienced the pain of discouraging real customers with ever-increasing manual reviews of transactions. We felt their pain and did our best to give them the smartest tools available to increase conversion rates and lower both their chargeback rate as well as the amount of manually-reviewed traffic.
In short, what this eCommerce fashion giant faced is more intense and globalized than other industries, but actually the same type of problems as what many other organizations face:
- The continuous growth of manual review of traffic, which was generated by legacy anti-fraud solutions providers;
- High chargeback ratios -- the company set a bold KPI to keep them below 0,5% for all of its brands;
- Weak chargeback risk detection, which translated into growing financial losses
Machine learning models depend on the quality of data they are fedWe created tech that sits in the client's environment, gathers myriad data points, and passes it on to the machine learning models which give actionable recommendations. We look at 5000+ data points, most of them non-declarative, proprietary data extraction methods regarding the user's hardware, software, network, and behavioral contexts, both web and native mobile; plus proprietary device marking techniques, 42 configuration based and 8 storage based. It is one-of-a-kind raw behavior understanding analytics necessary for hyper-personalized analysis in both web and native mobile contexts. It sets us apart from our competitors in the space (feel free to ask around).
Learn from past mistakesBut the good thing about coming into a project where there is a history of mistakes is the ability to learn from them, especially if you have a record of the mistakes made by previous systems! So Nethone took an iterative approach to model building. New models are built that target the incorrect predictions of previous model builds.
To detect chargebacks, the Nethone Data Science team implemented two supervised machine learning models. The goal of the first one was to detect chargebacks directly, while the second one was to replicate the results of the decision process of previous anti-fraud providers. Then, the DS team trained and tested multiple machine learning models using various statistical techniques. We found the best performing models and put them to work.
Final touchesLuxury goods eCommerce, like all online consumer goods platforms, see a sharp spike in purchases during the holiday season. The team scaled its data processing resources to ensure both models' predictions would not experience any downtime during important sales seasons, such as Black Friday or the winter holiday season.
Finally, Nethone has already successfully worked in so-called "risky geographies" and we have learned the attributes of real customers versus fraudsters and friendly fraudsters. So we passed on the knowledge to our client's tailored machine learning model. So the client continues to benefit from lessons learned from the experiences of our other clients.
In short, we learned from the past, tested multiple ML models in parallel, scaled for big events, optimized, opened up the client to new markets that were deemed risky, and optimized some more. We were able to cut down the platform's manual review rate by nearly 60%. At the same time, the percentage of accepted traffic increased in comparison to the rates of other anti-fraud solutions providers. The overall chargeback rate decreased by over 12%. For one of the fashion eCommerce platform's most valuable brands, the chargeback rate was lowered by as much as 89%. The company's internal KPIs were met -- the overall chargeback rate was kept below 0.5% for all of its brands. And all of it happened within four months of full integration.
Their fraud management team got to take a breather, too, as they had been burdened with growing manual review of transactions!
Caption: Reduction in manual review and chargebacks means lower costs for the company. Transactions with reduced friction improve the customer experience, which translates into customer loyalty and return purchases.
Nethone is a global provider of AI-driven KYU (Know Your Users) solutions that allows online merchants to understand their end-users and prevent online fraud. By using machine learning technology, Nethone is able to detect and prevent card-not-present fraud, including protection against account takeover. Founded in 2016 by data scientists, security experts, and business executives, Nethone successfully cooperates with eCommerce, digital goods, travel, and financial industries on a global scale.
There are no related Events
Manual Review remains a cornerstone of modern fraud prevention; offering enhanced precision in fraud screening, fairness in dispute management and labels for machine learning. However, as a business grows, so to must a Manual Review team. This introduces operational challenges to manage headcount, quality and return on investment.
In this session, we will cover Booking’s story of launching and rapidly scaling Manual Review Operations as a Service in Fraud Prevention. Hear how we empower a small team of 4 to manage Manual Fraud Operations on a global scale across Booking’s suite of products and associated risks.
As the need to reduce the cost of manual fraud prevention increases, we will show the benefits of leveraging multiple fraud prevention solutions such as outsourcing, automation and ML, demonstrating how the function interacts with various ML models to optimise workload and achieve a balanced defense against fraud.
Business leaders at global marketplace Wish knew the secret to the enterprise's continued growth was increased international expansion.
As one of the world’s largest e-commerce marketplaces, Wish now operates in more than 60 countries, processing approximately 900,000 transactions a day, across about 250,000 merchants, and has more than 20 million monthly active users. While that scale provides a wealth of transaction intelligence, Wish also needed to put a very local lens on the data it was processing.
Wish found its answer in machine learning — in particular a machine learning fraud protection model that scales rapidly while leveraging the fraud and risk expertise of the internal team at Wish. Smart machines surfaced the localized data the Wish team needed to react to the diversity of geo-specific fraud attacks and abuse schemes.
In this session, Signifyd senior vice president of operations and corporate development J. Bennett and Wish Director of Risk Operations Tara Mitchell dive into the considerations around deploying a machine learning solution and explore the steps Wish took to marry the strengths of humans and machines to reduce their exposure to fraud and increase order approval and conversion rates.
Conventional fraud detection has historically been centered around linear relationships between user indicators. Machine learning techniques in this domain also focus on learning and adapting to patterns arising from single depth connections of datapoints. The weak point of this setup is that we miss out on transitive relationships, which becomes an increasingly interesting factor when fraudsters reuse few overlapping indicators in new fraud attempts.
At Booking.com, we solved this problem by using graph technology to power our payment fraud controls. In this presentation we will show how we developed an in-house technological ecosystem that stores payments transactions in graph format and leveraged state of the art algorithms to compute innovative graph features that enriches our existing fraud controls (ML models and static rules). We will have a look at the different parts of the system: a latency sensitive real time feature computing service, a visualization tool for analysis of networks and a historical feature reconstruction mechanism. Finally, we will have a look at the impact we saw on our fraud controls after incorporating the new features.
We would conclude by explaining the plans to scale this technology in other fraud domains like marketing & rewards, account takeover etc. and exploring Network Representation Learning (a type of deep learning on graph data) to tackle them.
Machine learning continues to be an important tool for fraud mitigation specialists, but fraudsters are learning how to adapt.
The current landscape is now a battle against both automated and human-driven attacks. This presentation from Adyen and Microsoft explores the latest techniques in AI and ML to ensure the best customer experience and provide additional context for fraud decisions.
There are no related Surveys
False positives down, revenue up! Learn from an Experian fraud expert how machine learning strengthens fraud prevention, reduces false positives, and leads to new revenues.
Fraud prevention is one of the most exciting areas in commerce. However, it is also challenging to core business functions. This webinar will present how modern fraud prevention becomes more efficient through machine learning models and how this results in new revenue potential.
By participating in this webinar, the learner should be able to understand:
- State-of-the-art fraud prevention methods and current fraud figures
- How machine learning supports fraud prevention
- Why companies should rely on smart fraud prevention with machine learning models
We have met with many cases where analysts not only doubt themselves in their decision but also discouraged to take information into account that may not be considered as useful – not to mention the rise of Machine Learning in fraud prevention. Is our work that we do manually truly outdated?
Through examples we will re-explore the tools that we have at our expense and discuss how we can effectively use them in relation, from articulating sentences, to defining use cases and relying on AI.
- To find or regain the interest in the beauty of fighting fraud – making decisions that would be the key to stop the malicious activity yet keeping the mind open to changes.
- Utilising every aspect of the tool that are available and considering ways that we may have disregarded before and still could be useful, ultimately a boost for the year 2022 and to remain on the top of defense against harmful users.
In this thought-provoking session, we will share best practices on combining AI and ML with some of the more traditional approaches to mitigating online fraud and highlight why extensive cross-industry collaboration can help organizations strike the optimal balance between security and usability.
Types of fraud prevention systems which are payment-agnostic are addressed next, followed by a brief analysis of machine learning models which use no payment data. The broadcast concludes with a detailed Q&A session.
At SEON Technologies we have released new information on the collection countries that are most and least at risk of cyberattacks. We have also taken a close look at the most common types of cybercrime occurring in the US.
Dubbed the Global Cybercrime Report, the report explains how several countries are the safest in the world from fraud and other cybercrime. and why others are not. Our methodology for this research was based on how companies and public infrastructure are all being fairly well protected through both legislation and technology at their disposal.