Case Studies | Retail

Personalised product recommendations on AWS

Amazon Personalize Recommendation Engine

About

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

Challenge

The project focused on three areas.

Getting the data ready

Interaction and item data had to be shaped into the schema Amazon Personalize expects, with clearly defined fields for users, items, timestamps and event types, and optional demographic data incorporated where available.

Relevant recommendations

A model had to be trained, tuned and validated so that it recommended genuinely relevant products for each user, measured against Amazon Personalize's built-in accuracy metrics.

Something the team could own

The solution had to be deployed in the client's own AWS environment with the documentation and knowledge transfer needed for their team to retrain and iterate on it independently.

Solution

The work was delivered in clear stages, each with its own deliverable and sign-off, so the client could see value building at every step.

Real-time

Recommendation endpoint deployed for live inference

3

Datasets modelled: interactions, items and optional user data

Self-serve

Team equipped to retrain and iterate independently

By the numbers:

  • Real-time - Recommendation endpoint deployed for live inference
  • 3 - Datasets modelled: interactions, items and optional user data
  • Self-serve - Team equipped to retrain and iterate independently
Changes

The engagement delivered a trained, validated Amazon Personalize model and a live recommendation endpoint in the client's AWS environment, demonstrated against the agreed success criteria. The client's team was handed a solution they can operate, retrain and extend themselves.

  • Clean data foundation — Interaction and item data shaped to the Amazon Personalize schema and stored in Amazon S3.
  • Validated model — A recommendation model trained, tuned and checked against built-in accuracy metrics before deployment.
  • Live recommendations — A real-time or batch endpoint serving tailored product suggestions, with integration reference code provided.
  • Ownership — Documentation, a runbook and a knowledge-transfer workshop so the client can maintain and retrain the engine.
  • Handover — Final review and sign-off, with AWS funding and credits explored to support the build.

With a working recommendation engine in place, the client can iterate on recipes and incorporate richer demographic data over time to sharpen relevance further as their catalogue and customer base grow.

AWS Stack

Amazon Personalize

For training and serving personalised product recommendations.

Amazon S3

For storing the prepared interaction and item datasets.

AWS Identity

And Access Management for controlled access to data and services.

Amazon Personalize

Campaigns and endpoints for real-time and batch inference.

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.