#Web

#Startup

#Crypto

Enhancing Fraud Detection Efficiency with Interactive Data Visualization

Doubled daily task completion rates for 25 internal risk analysts at Binance, increasing suspicious money inspection cases per analyst from 10 to 20 per day by designing an interactive data visualization tool that streamlined the table-based fraud detection system.

End to end design

3 months

1 PM, 1 designer, 5 dev

Why this is a challenge?

The Risk Team's had to manually record data and draw connections to spot fraud among Binance users due to an inefficient table format of their interface.

Our solution to the issue

Created a data visualization tool that boosted risk analysts's task completion rate by 2x and indirectly boost customer satisfaction and engagement. Before diving into my design process, here’s a direct comparison of the redesign.

Redesign comparison

Before

Problem

This list view presents detailed data for each item, but the trade-off is that it makes comparing relationships between entries difficult and locating specific data challenging due to the long scrolling table.

Problem

After

Solution

The diagram features a center-outward layout for easy navigation, with expandable and collapsible elements to display hierarchical data. Additionally, it highlights different transaction statuses with icons, helping users quickly locate and identify the data. Check my design rationale

Solution

So what is Binance fraud detection system?🛡️

Due to rising crypto fraud, Binance formed a risk team to investigate suspicious transactions. Cutomers can report issues, and analysts will use fraud detection tools to review transaction histories and track funds.

Peter Wang
Binance risk analyst for 3 years

Brief

I’m highly frustrated with the current data analysis platform.

JTBD

When analyzing data, I want a tool that quickly locates and identifies information, so I can efficiently separate queries and sort flow direction.

To uncover risk analysts’ pain points, I conducted 25 internal interviews and found that they need faster ways to locate and identify information.

From 25 internal user interviews, I learned that analysts want to quickly locate and identify information

Peter Wang
Binance risk analyst for 3 years

Brief

I’m highly frustrated with the current data analysis platform.

JTBD

When analyzing data, I want a tool that quickly locates and identifies information, so I can efficiently separate queries and sort flow direction.

Users were also frustrated with manually sorting data when investigating suspicious transactions in the old system

Findings

After interviewing, I focused on the three key pain points most frequently highlighted by analysts with the current table format tool.

Unclear asset flows in theft cases

Lack of clarity when investigating user asset flows in theft cases.

Difficulty comparing data from cross columns

Difficulty from the need to divide queries across multiple modules.

Manual Effort in Identifying Downstream Counterparties

Difficulty from the manual effort needed to identify downstream counterparties.

Our goal is to increase Binance’s daily case inspection rate by 1.5x, helping retain customers through stronger support for hacked funds and suspicious transactions.

" How might we enable internal risk analysts to locate and identify data, allowing them to complete their daily suspicious money inspections more efficiently? "

" How might we enable internal risk analysts to locate and identify data, allowing them to complete their daily suspicious money inspections more efficiently? "

I was inspired by correlation diagrams, dot-connecting patterns, and the concept of progressive disclosure

Key insights I learned:

Initial design with data linked to relevant information

However, users struggled with navigation

2/25 users found the data relationships clear
1/25 users found the hierarchy clear
3/25 users found navigation clear
4/25 users found the context clear
1/25 users found scalability easy

Redesigned the diagram with a progressive, direction-oriented view to make navigating data relationships easier.

Based on user feedback, which emphasized the need for a diagram that clearly displays data hierarchy and is easy to explore with large datasets, I revisited my research and iterated the design. I incorporated the key concept of a correlation diagram, using a progressive view to represent complex data hierarchies and adding arrows to indicate transaction direction.

Easy to explore

Starting point from center to outward to help users easy to navigate

Easy to navigate complex dataset

Expand and collapse to display hierarchical data

Expand and collapse to display the hierarchical data

Arrow and icon

It shows the transaction status and direction (deposit, withdraw, C2C)

Iterated on diagram UI to align color usage with data hierarchy

After redesigning the diagram, I conducted a usability test with the same 10 users, achieving an average score of 92% (23/25) for user feedback, an improvement over the previous 5 benchmarks. After communicating with the PM and developer, I proceeded to work on the UI for the diagram.

From the first to the final version (left to right), I made color design decisions based on insights from the PM. I learned that the data hierarchy is: transaction status > transaction direction > counterparty user. I highlighted colors according to this order, which led to positive feedback from users.

Copy Paste from Figma

Install the Figma plugin and you’re ready to convert your designs to a responsive site.

Start with Site Templates

Browse dozens of professionally designed templates. Click, duplicate, customize.

Create prototypes to align developers & PM and train the internal analysts to use

Impact on the internal organization and Binance customers

After three months of implementation with the risk team, we observed a significant impact on internal operations and received positive satisfaction survey results from Binance users reported to the risk team. The daily case investigation completion doubled, surpassing the KPI metric of 1.5x.

Binance customer

1.8x

Rise in NPS satisfaction survey scores

Binance users reporting to the risk team increased their satisfaction from 50 to 90, according to the NPS survey.

Binance internal analyst

Pass the KPI 1.5x

Increase in daily case investigation completion

Internal analysts boosted daily case investigations from 10 to 30, reducing labor costs and enabling the team to focus on higher-priority tasks.

Binance customer

1.8x

Rise in NPS satisfaction survey scores

Binance users reporting to the risk team increased their satisfaction from 50 to 90, according to the NPS survey.

Binance internal analyst

Pass the KPI 1.5x

Increase in daily case investigation completion

Internal analysts boosted daily case investigations from 10 to 30, reducing labor costs and enabling the team to focus on higher-priority tasks.

Challenge & reflection

✅

We initially struggled with complex design requirements, and the development team had difficulty achieving the ideal data shape.

✅

To overcome this, I shared the user testing results with the team and led the effort to research and collaborate with the PM and developers to create an effective diagram formula.

✅

This approach not only met user needs but also empowered the team to tackle technical challenges. The successful implementation resulted in a 3x increase in internal work efficiency.

More projects

Microsoft

Word co-agent

Microsoft

Word co-agent

Uppermed

Health app

Uppermed

Health app