HMRC

Equal Experts supports the tools that help HMRC identify tax fraud

How the Illuminate platform shines a light on unstructured data

Equal Experts have helped build Illuminate, an enterprise search and discovery platform built using open-source technologies, for HMRC.

The platform has enabled HMRC to identify millions of pounds in additional yield by uncovering potential tax fraud before it impacted the UK taxpayer.

It includes a front-end search tool and reusable data pipeline that allows HMRC to access, export and search unstructured and semi-structured data from millions of documents. This includes PDF files, letters, and images that would previously have been checked manually. 

Using Illuminate, HMRC teams can quickly search large volumes of data to identify compliance issues or criminal activity.

About the client:

HMRC is a non-ministerial department of government. It is the UK’s tax, payments and customs authority, and has a vital purpose: gathering the approximately £740b tax revenue that pays for the UK’s public services (hospitals, schools, etc.), and helping families and individuals with targeted financial support.

  • Industry:

    Industry icon

    Government

  • Organisation Size:

    Organisation icon

    66k+

  • Location:

    Location icon

    UK

  • Services:

    Services icon

    Platform Build

  • Length of project:

    Ongoing

The challenge: unlocking value from unstructured data

Since the introduction of online filing, HMRC has received more than 60 million sets of company tax returns, which often include attachments such as PDF files and images. Equal Experts found that it was very difficult for HMRC to search this semi- and unstructured data in an effective and efficient manner, making it harder to identify certain types of fraud that were hidden in plain sight in unstructured data.

The solution: a risk profiling tool that’s easy to query at scale

Illuminate is a risk profiling tool that gives HMRC the ability to search across millions of documents to identify tax at risk and criminal fraud. Our collaborative work with HMRC on the Illuminate platform has enabled its users to bulk-search unstructured and semi-structured data to identify non-compliance and fraud more rapidly. By increasing their access to data, Equal Experts has helped drive intelligence that is critical in responding to the threat of organised crime.

A key achievement of our work together was to build in automated scheduling of specific queries; this helps HMRC to identify fraudulent tax credit claims before they are paid. This means HMRC makes enormous savings in time, money and resources compared to trying to recover payment later through tax investigations.

Equal Experts and HMRC formed a mixed team of consultants and civil servant engineers, who worked with numerous business areas across HMRC, various suppliers and other government agencies to ensure that users would have access to the most recent data available, whenever they needed it.

Making the impossible easy with open-source technologies

Together, we created a unique ingestion pipeline for the platform, which extracts the entire content of documents, including unstructured text and digital or structured data. No other IT tool on the HMRC estate has this functionality with this scale and variety of data.

We made incremental improvements to create a performant, resilient, microservice-based solution. Crucially, this pipeline can be reused, allowing the data to be made available to other teams and agencies, such as data scientists, for use in creating large machine learning applications.

The result: Millions in tax risk identified

Illuminate has unlocked data that would previously have taken hours of manual search to discover. We’ve made it possible for users to now easily – and at scale – query the platform to identify possible risk, with the result that: 

  • Millions of £ in confirmed tax at risk for Counter Avoidance has already been identified
  • Savings of tens of millions have been made for the exchequer by stopping fraudulent claims being paid.

Illuminate has also contributed to policy changes within government and has resulted in the wider identification of significant tax yield through Risk Intelligence Service compliance projects. The platform enables cross-government joint working between HMRC and agencies such as Companies House, the Insolvency Service and the Department for Business, Energy & Industrial Strategy (BEIS). It has also identified millions in fraudulent tax credit claims for FIS (Fraud Investigation Service).

Conclusion:

The Head of Core Products for Data Platform Services commented at the time: 

“The Illuminate Team has set the standard for agile delivery, demonstrating the benefits of close cooperation between a passionate business-based product owner, capable developers and a strong delivery focus. They have built a reusable, reproducible data pipeline using open source products and standards, and  comprehensive search capability. The ability to unlock unstructured data is critical to HMRC’s strategy of being data driven and exploiting the vast amount of resources previously locked in silos. The fact they have been successful is no surprise, but the scale of the success is staggering.”

We’re incredibly proud of the work we did to bring the value of this tool to HMRC. The fact that Illuminate was built whilst simultaneously maintaining the critical national infrastructure that serves the UK taxpayer makes it even more remarkable. Moreover, it is a product which has met and surpassed all expectations, offering support and opportunities for wider areas of government to improve their own risk analysis.

 

Watch the case study video:

You might also like...

Want to know more?

Are you interested in this project? Or do you have one just like it? Get in touch. We'd love to tell you more about it.