Automated handling of payment processing anomalies

17 Submissions
Collaboration with Seeker
Challenge under evaluation

Challenge overview


HM Revenue & Customs (HMRC), the Seeker for this Wazoku Crowd Challenge, is looking for new software technologies or system approaches to improve their automated payment receipt processing to reduce or remove the costly manual intervention required in the current process.

HMRC has a complex referencing system that leads to customers needing to submit a number of references when making payments, leading to problems.

Customers are in most cases individual citizens.

Customers can easily submit insufficient or incorrect supporting references that the ‘payments in’ process then fails to automatically handle. The payments falling outside of the standard process drop into a separate exception handling team with limited automation capability, causing a significant manual intervention cost and increased customer contact demands. 

This is a Scouting Challenge seeking a partner or supplier to provide systems or expertise to solve HMRC’s business challenge; the Solver is invited to submit a written proposal to be evaluated by HMRC with the goal of establishing a collaborative partnership.

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on the 8th of January 2024.

- Login or register your interest to start to start collaborating!



HM Revenue & Customs (HMRC) is a government department in the United Kingdom responsible for administering and collecting various forms of taxation and enforcing tax laws. It plays a central role in the country's fiscal system and is tasked with ensuring that individuals and businesses pay the taxes they owe.

Find out more about participation in Wazoku Crowd Challenges.




HMRC handles large volumes of payments received from customers via its banking provider. There are multiple payment methods a customer can use for example, bank transfer, credit or debit card, faster payment or cheque.

Customers are in most cases individual citizens.

Often their payments have incomplete or inaccurate transactional data that means the payments can’t be automatically allocated to their customer account. These unhandled payments result in time-consuming and resource intensive actions to manually ‘data match’ and reconcile posing issues for financial administration.

The main problems which lead to payments requiring manual intervention are:

  • Unrecognisable references, either incomplete, incorrect or blank
  • Payment and liabilities don’t match
  • Multiple liabilities in a single payment
  • Customer’s identity is not clear

Payments and accounting at HMRC uses the SAP ECC 06 platform, with plans to move to SAP S/4HANA.

HMRC is exploring opportunities to enhance its automation capabilities for dealing with these complex payment anomalies. They are interested in understanding how software technology or system approaches available in the market are being used to address challenges with payment processing anomalies e.g. decision automation. Could Machine Learning and Artificial Intelligence (AI) play a role to streamline processes, reduce errors, improve financial management and reduce or remove manual intervention?

Since 2021 HMRC has been capturing structured data that demonstrates the manual payment matching solution. This data is available to be used in designing future matching processes, as part of the collaboration.



The current rule-based automation for dealing with exceptions has limited capabilities and at present is limited to data matching. This process uses the received payment data and looks for historical payments made with the same bank details, then scans across the accounting systems to identify and match the customer and any open liabilities to the payment.

There is no present method of predetermining (positive or negative) which payments need further examination. While the majority of inputs received are compliant, an improvement would be to assume all payments received are first treated as suspect until each needed criterion has been fulfilled, before moving to the next stage of processing. 

The requirement for the many payment transaction anomalies, is to find an automated way to replicate the decision making that is currently done manually to match payments to liabilities. Things to consider:

  1. We may have no bank details on record
  2. Details that we do have on record are not provided with the payment
  3. A sequence of data based decisions (decision tree) need to be followed to find a correct home for the payment, simulating human intelligence
  4. Auto allocation of multiple liabilities that can be received with a single payment
  5. Automatically trigger communication with the customer when more information is needed

HMRC plans to increase automation capabilities in 2024 and over the ensuing years.

HMRC is interested in receiving proposals from Solvers who can supply or have experience with an existing software product(s), or who can develop a new software approach that automates and improves the efficiencies of the payments receiving processes. Solutions should enable improved data or payments allocation accuracy and consistency, thereby reducing error rates.

The new system will need to receive the input data, as well as be able to export data into an existing SAP implementation.

HMRC is primarily interested in solutions with the potential to meet the following requirements:

  1. Be compatible with SAP ECC 06 and SAP S/4HANA
  2. Offer advanced decision tree logic for complex data matching
  3.  Augment the current manual process through information presentation to Caseworkers to enable swift validation of partially automated decisions i.e., presenting historical transactional information, and previous resolution activity to aid decision making for new cases
  4. Implement learning technologies like Artificial Intelligence and Machine Learning
  5. Ability to thoroughly flag and scan for all related open payment work items for a customer across the ‘multi-system / ‘multi-process’ technical landscape, so that all the open work items for the customer are resolved at the same time.
  6. The capability for HMRC to improve/configure the solution after initial implementation
  7. Have scalable capacity to process at least Sixty (60) Million cases per year, and 1.5 Million cases on a daily bases at specific cyclical peak periods throughout the year
  8. Provide near-real-time status visibility for audit and reporting
  9. Provide escalations and notifications as needed

HMRC is open to all suggestions and levels of innovation; however, any solution needs to be able to interface with SAP ECC 06 and migrate to SAP 4HANA in the future.

Since 2021 HMRC has been capturing structured data that demonstrates the manual payment matching solution. This data is available to be used during the collaboration in designing future matching processes. 

Proposed solutions with Technology Readiness Levels (TRLs) 6-9 are invited outlining existing or evolving software technologies and/or relevant associated expertise.

This is a Scouting Challenge, which has the following features:

  1. HMRC will evaluate your submission to determine their interest to contact you for further business and collaboration discussions.
  2. If further contact is requested, you can negotiate the terms of the contract (including scope of work, tasks and duration) directly with HMRC.
  3. The monetary value of any contract will vary depending on the amount of work to be delivered and the agreed upon time frame.



Please login and register your interest, to complete the submission form.

The submitted proposals must be written in English and can include:

  1. Participation type – you will first be asked to inform us how you are participating in this challenge, as a Solver (Individual), Solver (Organization), or Expert.
  2. Solution Stage - the Technology Readiness Level (TRL) of your proposal, TRL1-3 ideation stage, TRL4-6 proof of concept stage, TRL7-9 production ready stage or not applicable (if your submission is as an expert).
  3. Problem & Opportunity - highlight the innovation in your approach to the Problem, its point of difference, and the specific advantages/benefits this brings (up to 500 words).
  4. Solution Overview - detail the features of your proposal and how they address the Solution Requirements (up to 500 words, there is space to add more, and to add any appropriate supporting data, diagrams, etc).
  5. Experience - Expertise, use cases and skills you or your organization have in relation to your proposal (up to 500 words).
  6. Solution Risks - any risks you see with your solution and how you would plan for this (up to 500 words).
  7. Timeline, capability and costs - describe what you think is required to deliver the solution, estimated time and cost (up to 500 words).
  8. References - provide links to any publications or press releases of relevance (up to 500 words).

Wazoku encourages the use by Solvers of AI approaches to help develop their submissions, though any produced solely with generative AI are not of interest.

Find out more about participation in Wazoku Crowd Challenges.

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on 8th of January 2024.

Late submissions will not be considered.

Your submission will be evaluated by the evaluation team first reviewing the information and content you have submitted at the submission form, with attachments used as additional context to your form submission. Submissions relying solely on attachments will receive less attention from the evaluation team.

After the Challenge submission due date, HMRC will complete the review process and make a decision with regards to potential collaboration(s) according to the timeline in the Challenge header. All Solvers who submit a proposal will be notified about the status of their submissions.

Use the slider to explore how the Challenge process works:


Review & Accept



To start solving this Challenge, log in to the Challenge Center or register as a Solver

Visit the Wazoku Crowd Community to start the conversation