dVector

Real-time Management of Fraud Services

 

Lead Product Designer

DataVisor: Company Overview

DataVisor is the leading fraud detection platform powered by transformational AI technology. Using proprietary unsupervised machine learning algorithms, DataVisor restores trust online by enabling organizations to proactively detect and act on fast-evolving fraud patterns, and prevent future attacks before they happen. Combining advanced analytics and an intelligence network of more than 4B global user accounts, DataVisor protects against financial and reputational damage across a variety of industries, including financial services, marketplaces, ecommerce, and social platforms.

dVector: Project Overview

DataVisor is the leading fraud detection platform powered by transformational AI technology. Using proprietary unsupervised machine learning algorithms, DataVisor restores trust online by enabling organizations to proactively detect and act on fast-evolving fraud patterns, and prevent future attacks before they happen. Combining advanced analytics and an intelligence network of more than 4B global user accounts, DataVisor protects against financial and reputational damage across a variety of industries, including financial services, marketplaces, ecommerce, and social platforms.

GOAL

Build a product to empower the fraud team to review fraud signals and make decisions with actionable insights, a streamlined flow, and seamless collaboration. 

PROBLEM
  • One of Datavisor’s core design problem is teaching the fraud teams to understand and trust results from its complex machine learning algorithms. Without that trust, they will not adopt the product.

  • Large volumes of cases to review. Currently, ~50% of fraud management budgets goes to manual reviews. 

  • Fragmented workflows, Ad-hoc review process, and limited fraud relevant information for decision.

  • Tailor the experience for different personas of the fraud team. Though there were multiple personas in the fraud team like fraud analyst, fraud manager, chief risk officer(CRO), etc. most existing fraud applications are designed to cater just the needs of the fraud analyst persona - which is to review and investigate alerts.

SOLUTION
  • The new design presents intuitively important information first, in a format that’s familiar to merchants.

  • By reviewing dozens/hundreds of accounts at once, the team was able to improve moderation efficiency and free up time for cases that require deeper investigation.

OUTCOME

110 Accounts/min

Review and decision speed using dVector

69x

Improvement in moderation efficiency

5x

New Customers

3X

Increase in this product usage from existing customers

400%

Increase in Revenue

7x

Number of countries this product is used

WHO ARE OUR USERS?

Debbie's pain points

Debbie starts her day by first reviewing all the new clusters and events that were detected by Datavisor from the last time she logged in. Then she moves on to monitor the investigation status of the events in the queues that she created and create new queues if necessary and assign them to analysts. On a regular basis, she reviews the workload, the

Fraud Team Manager/Team Leader - Debbie

Typical Workday

Debbie starts her day by first reviewing all the new clusters and events that were detected by Datavisor from the last time she logged in. Then she moves on to monitor the investigation status of the events in the queues that she created and create new queues if necessary and assign them to analysts. On a regular basis, she reviews the workload, the performance, and the actions that the fraud analysts took in the system.

 

In a nutshell, Debbie is responsible for making sure the work has been assigned based on the bandwidth of the analysts, monitor their performance and their actions, and finally, make sure that fraud is stopped before they incur the loss.

Fraud Investigation Analyst - Mark

Typical Workday

Mark starts his day off by first checking his workload for the day by checking the number of new clusters that were assigned to him by Debbie(the manager) and the number of events that were pushed to his queue for investigation. He then proceeds to investigate one cluster or event at a time and takes necessary actions. Mark can also escalate by assigning the clusters/events to the senior analysts by reassigning in case he thinks it needs further investigation. 

Mark's pain points

Debbie starts her day by first reviewing all the new clusters and events that were detected by Datavisor from the last time she logged in. Then she moves on to monitor the investigation status of the events in the queues that she created and create new queues if necessary and assign them to analysts. On a regular basis, she reviews the workload, the

Scott's's pain points

Debbie starts her day by first reviewing all the new clusters and events that were detected by Datavisor from the last time she logged in. Then she moves on to monitor the investigation status of the events in the queues that she created and create new queues if necessary and assign them to analysts. On a regular basis, she reviews the workload, the

Chief Risk Officer - Scott

Typical Workday

Scott typically does not use our system on a daily basis but on a weekly or a bi-weekly basis for reporting purposes. He uses Datavisor fraud cockpits to check the fraud exposure or the kind of fraud that their org is exposed to. He also may want to check the performance of our models, see the amount of fraud Datavisor stopped, and the dollar amount that was stopped from losing to fraud.  Scott also creates and schedules timely reports like quarterly reports using the reporting infrastructure.

CONCEPT SKETCHING
CONCEPT SKETCHING
PRODUCT ARCHITECTURE AND DESIGN
Workflow 3: Rules Engine

Augment the simplicity of a rules engine with the scalability and capabilities of machine learning, and the sophistication of advanced AI-powered features, to safeguard your organization from modern fraud attacks. DataVisor’s Advanced Rules Engine integrates with the Feature Platform to power early detection with enriched fraud features.

Heuristic analysis of existing rules engine, Stakeholder interviews, Brainstorming sessions, Affinity diagram, Customer interviews, Usage analysis with Google Analytics
SKETCHES
HI-FI INTERACTIVE PROTOTYPES
Hueristic Analysis: Sample Report

Conducted a thorough heuristic analysis of the existing workflows and submitted a meticulous report on the issues identified with the severity level and the suggested solution.
(Samples..)

Usability testing: Sample

Collected feedback from the internal stakeholders as well as end users at different stages of design. Below is the sample of usability testing which I conducted for a reporting feature. The same exercise is carried out for each new design.

the outcome

The introduction of new dashboards, enhanced rules engine design and the new workflows increased the number of customers using our platform's UI directly. Earlier, only 3 of our customers used our UI for fraud investigation and the rest (>30) integrated our detection results in their in-house fraud detection products. Now, in the very short period after the new design, at least 12 customer use our UI for their day-to-day fraud investigations.

1. Robust rules management workflows

Once a complex workflow, with the new design the user can easily create and update a rule. The user can also track the efficiency of the rule and modify and test it on the fly by seeing the users detected by the rule.

2. Efficient and clean model setup, tuning and deployment process

The old model setup process was unstructured and involved numerous steps across multiple screens and it also needed a steep learning curve and time to understand. As a result, the new trial engineers took weeks to familiarize themselves with the process. The new model setup workflow allows the user to easily setup the model and tune the algorithm while seeing the output at each stage. The new design is so simple that even the sales and marketing team uses the actual setup to demo the product.

3. Comprehensive and contextual user information for fraud investigation

One of the primary use cases of the product is to facilitate the customers to review the detected users and investigate if they are fraudulent. With the new design, the customers can see more comprehensive and contextual information during the fraud review process. And, they can also take quick actions like labeling the users as Good/Bad, adding a note or blocking the user.