Keynote - Graph Technology
This presentation, from Jörg Schad of ArangoDB, explores how machine learning models based on graphs can incorporate relationships inside data explicitly, while also highlighting the many powerful Machine Learning algorithms that already use graphs, e.g., Page Rank (Pregel), Recommendation Engines (collaborative filtering), text summarization, and other NLP tasks.
The keynote also highlights the recent developments regarding Graph Neural Networks and how they connect the worlds of Graphs and Machine Learning even further.
Some content is hidden, to be able to see it login here Login
Host a Webinar with the MRC
Publish Your Document with the MRC
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.
There’s a big gap in digital commerce. Merchants have very detailed data on their entire customer journey up until one of the most critical points: the payment. At that point, many are lacking clear visibility and real insight into their approval rates and other business metrics, often resulting in loss of revenue and higher total cost of payments acceptance. This is mainly due to unclear or insufficient payment data—payment data with which they could easily answer questions like Why are 15% of my orders declined and what could/should I do about that? Most merchants don’t have easy access to the answers.
Participants in the ecosystem such as payment gateways, payment service providers (PSPs), third-party fraud tool providers, BIN service providers, acquiring banks, card brands, and issuing banks (and APM schemes) must all come together in some capacity for a single payment to go through successfully.
All these layers between buyers, merchants, and approved transactions have different technology standards, formats, data fields and, most importantly, definitions of data and data fields—both in what is sent out (for approval) and what comes back (in response). It all adds up to a huge challenge for businesses to easily access and turn payments data (whether from one or many PSPs/processors) into actionable insights. How can you improve performance if you don’t know what to tweak or why? How can you monitor any changes over time?
All merchants have some form of blind spots in their payments data that can help them uncover and address costly issues or opportunities to improve. And what could be more relevant today—in an economy where companies, teams, and people are being asked to do more with the same (or less) resources—than finding ways to optimize your existing payment stack?
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.
Ultimately, in the world of payments, success depends on human factors, like how consumers perceive and respond to risk, reward and effort.
Against this backdrop, Token surveyed over 1,000 people across Europe about the attitudes, preferences and behaviours shaping their financial and digital lives.
Token presents: "Who Will Pay by Bank" a data-driven look at the human element that will fuel the future of open banking payments.
A glimpse into this report:
- Learn which consumers are paying by bank today and where will we see demand tomorrow
- Discover the behaviours and opportunities that could support continued uptake of account-to-account (A2A) payments
- Understand how consumers in Europe perceive the benefits of A2A payments and other payment methods on a country-by-country basis
- Uncover how consumers understand open banking's evolving role in their lives
- Read commentary from the Open Banking Implementation Entity, Open Banking Expo, American Express, Ban
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.
Open banking in the UK and EU has created a new online payment option: instant bank transfers, which offer lower fees, better security and more convenience for consumers. In February of 2021, more than one million open banking payments were processed in the UK, compared with 300,000 for the whole of 2019. But how mature is this payment option, who’s already using it and will consumers adopt it?
Join TrueLayer and guests, as we cover: What open banking payments are and how they work - The retail trends that are driving the growth of this new payment option - Is the time right? A status check on usage, adoption and readiness of open banking payments in the UK and Europe - How open banking payments drive value for ecommerce merchants - The consumer payment experience: demo of UX + real case studies - Consumer protections for open banking payments.
In Nethone's Frictionless white paper, you will learn:
- How to reduce checkout friction to maximise your revenue?
- How to manage UX friction associated with PSD2/SCA?
- How to prepare for Transaction Risk Analysis (TRA)
- How to keep your customers happy
- How to achieve all this while effectively combating payment fraud
This whitepaper begins with a snapshot of PSD2 and summarizes the directive's main changes, focusing on SCA. After highlighting how SCA will affect financial services companies, the paper examines how biometrics can meet SCA requirements while avoiding unnecessary friction. The document concludes with an overview of Nuance's biometrics solutions.