Case Studies | PropTech

Sharper scoring from sensor data

SageMaker Model Construction

About

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

Challenge

The engagement targeted four focus areas across the pipeline.

Faster, more efficient model training

Training cycles were slower than the team wanted. The first focus was to bring in SageMaker AutoML so models could be trained and iterated within a reasonable, predictable timeframe.

Low-latency, reliable scoring

Scores needed to be returned quickly and dependably. The second focus was to connect SageMaker's inference API directly to the existing APIs, so Lambda functions could call the model for scoring with better response times.

Scalable feature and data management

Features were being managed directly in S3, which did not scale cleanly. The third focus was to adopt the SageMaker Feature Store for faster, more consistent feature extraction and reuse.

Accuracy that holds over time

A static, binary model degrades as data shifts. The final focus was to explore automated monitoring for data drift, continuous training, and a move to multi-classification to widen the insight the pipeline could produce.

Solution

Cloud Combinator ran the engagement as a Cloud Accelerator, combining discovery and consultancy with expert-led workshops and delivery directly in the client's AWS environment.

7

SageMaker capabilities integrated or explored across the pipeline

Multi-class

Classification expanded beyond the original binary model

~4 wks

Cloud Accelerator delivery window

By the numbers:

  • 7 - SageMaker capabilities integrated or explored across the pipeline
  • Multi-class - Classification expanded beyond the original binary model
  • ~4 wks - Cloud Accelerator delivery window
Changes

Cloud Combinator delivered the enhancements against the agreed Cloud Accelerator scope, demonstrating Amazon SageMaker as a suitable, end-to-end ML platform for the client to continue building on. The engagement also signed off the technical competence of the client's internal lead to carry the work forward.

  • Faster training with AutoML — SageMaker AutoML streamlined model training, making iteration quicker and more predictable.
  • Direct, low-latency scoring — The SageMaker inference API was wired into the existing APIs so Lambda can call the model directly, improving scoring response times.
  • Cleaner feature management — The SageMaker Feature Store replaced ad hoc S3 handling with faster, more scalable feature extraction and reuse.
  • Ready to improve over time — Automated drift monitoring, continuous training and multi-classification were explored to keep accuracy high as data evolves.
  • Handover — Included an immersion day and hands-on labs so the client's engineers can continue developing the model with confidence.

With its scoring pipeline modernised on SageMaker and its team upskilled, the client is positioned to keep refining accuracy, extend into richer multi-class insight and scale the product on AWS. Cloud Combinator went on to conduct a Well-Architected Framework Review to harden the wider environment for production growth.

AWS Stack

AWS Lambda

For serverless scoring calls into the model from the existing APIs.

Amazon S3

For storing validated sensor data and training datasets.

Amazon Kinesis

For streaming sensor readings into the pipeline.

Amazon API Gateway

For exposing the scoring service to the client's application.

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.