Our client wanted to assimilate data from companies across their portfolio to create a centralised hub where advanced analytics and machine learning models could be applied to the consolidated data.
We were required to build out the data hub and begin to generate insights that could be leveraged by the individual portfolio companies and the wider group.
What we did
✔︎ Extracted, cleansed and standardised subsidiary company data into a central repository
✔︎ Enriched the repository with open datasets to provide a richer view of customer coverage across the portfolio
✔︎ Delivered two machine learning models focused on identifying cross-selling opportunities and credit risk scoring
Analysts within the portfolio companies and the wider group can now perform ad-hoc analysis and machine learning projects within the data hub. The central hub serves as a centre of excellence for advanced analytics and data science.
In addition, our first machine learning model identified cross-selling opportunities between the portfolio companies, enhanced by multiple open data sources. Our second model scores customers for credit risk, given their behaviour on the platform.
We handed over a fully documented, reproducible codebase and cloud infrastructure, as well as whitepaper reports highlighting the most valuable future application of machine learning on the platform.
rows of data across 6 portfolio companies used to generate cross portfolio insights.
How we did it
We worked with a small team who serve the two sides of the business: private equity and lending. They wanted to better understand their customer base and coverage across the UK, and use machine learning to explore use cases around credit scoring, risk management, fraud detection and price optimisation. In order to deliver such projects, we need to create a central data repository and onboard analysts within the company who could deliver future projects.
To achieve this, we built a ring-fenced Azure environment closely tied to the existing infrastructure where the raw data is stored as flat files in Azure blob storage, and ETL pipelines created in Azure Data Factory to move the datasets into a SQL Server database. The infrastructure and pipelines were thoroughly documented and presented back to the client in a show-and-tell session.
After sourcing and loading data into the environment, we built and tested a cross-selling propensity model and an enhanced credit-scoring model, handing over reproducible code and whitepaper reports to internal stakeholders. The company is now able to rapidly iterate on analytical ideas and is at the forefront of technological innovation.
Looking to run a similar project?
If you’re interested in finding out more about our services and how they can transform your business, get in touch and we'd be happy to tell you more.