Case Studies | SaaS B2B

Matching officials to matches with AI

OfficialGame Recommendation

About

A SaaS B2B business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The challenge had three focus areas that shaped the build.

Turning history into recommendations

The client held rich records of past assignments, referee profiles and post-game ratings, but that data was not being used to guide new bookings. The first focus was to make historical context available to a model at the moment an organiser submits a fixture, so it could suggest the most suitable referee.

Pricing a fixture fairly

Fees varied with match level, sport, timing, notice period and a referee's experience and travel. The second focus was to predict an appropriate fee for a given fixture from historical fees paid, removing guesswork and inconsistency from the pricing conversation.

A production-shaped, low-cost footprint

As an early-stage product, the client needed a serverless, pay-for-use architecture that stayed inexpensive at low volumes but was ready to scale, deployed reproducibly as code in their own account with a clear handover.

Solution

Cloud Combinator delivered the engagement as two tasks that share a common AWS foundation of S3 for data, Lambda for orchestration, API Gateway for access and AWS CloudFormation for reproducible deployment.

2

AI models delivered: a Bedrock recommendation engine and a SageMaker fee model

1,000/mo

Request volume the architecture was sized for (projected)

12.5

Days of focused build effort across both tasks

By the numbers:

  • 2 - AI models delivered: a Bedrock recommendation engine and a SageMaker fee model
  • 1,000/mo - Request volume the architecture was sized for (projected)
  • 12.5 - Days of focused build effort across both tasks
Changes

Cloud Combinator delivered both workstreams against the agreed success criteria: a LLM-based recommendation engine that generates referee suggestions from historical assignments and profiles, and a SageMaker model that predicts appropriate fees from historical data. Both were deployed as infrastructure as code in the client's AWS environment, tested end to end, and handed over with documentation and a knowledge transfer session.

  • Recommendations from real history — Sport and location partitioning in S3 gives the model relevant, right-sized context for every fixture, so suggestions reflect the client's own data rather than generic rules.
  • Consistent, data-driven pricing — The XGBoost model turns historical fees and fixture features into a predicted fee, giving organisers a fair, repeatable starting point.
  • Serverless economics — A Lambda, API Gateway, S3 and on-demand model design keeps cost low at early-stage volumes while leaving clear room to scale.
  • Reproducible and owned — Everything was deployed via AWS CloudFormation in the client's own account, so the platform is theirs to run, audit and extend.
  • Handover — Included a working demonstration, technical documentation and a knowledge transfer session so the client's team understood the design decisions behind the build.

With two AI capabilities now proven on AWS, the client has a foundation it can build on, refining the models as more match data accumulates and extending the same serverless pattern to new sports and competition levels. Cloud Combinator recommended a Well-Architected Framework Review as the natural next step to harden the solution for production scale.

AWS Stack

Amazon SageMaker

For training, evaluating and hosting the XGBoost fee prediction model.

AWS Lambda

For serverless orchestration between the API, data and models.

Amazon S3

For partitioned storage of historical match and referee data.

Amazon API Gateway

For exposing the recommendation and pricing service to the platform.

AWS CloudFormation

For reproducible, infrastructure-as-code deployment in the client's own account.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.