Banking and lending solutions > Transaction Categorisation and Enrichment

Transaction Categorisation and Enrichment

Prevent messy and unrecognisable transactions by accessing the market-leading data categorisation and enrichment engine. Powered by machine learning and used by leading banks.

Transform critical lending and affordability decisions from ambiguous to effortless. Gain a better understanding of your customer to segment, nudge and match them to the relevant products.

Start leveraging your existing data lakes (or add new ones) when you combine better accuracy with broad merchant coverage to reduce risk and operational costs.

Cut out 22% of customer service calls

We help customers instantly recognise their spending, and stop wasting the precious time of your customer service team. Turn confusion into clarity, and cut out 22% of calls from confused customers.

Our unique engine combines merchant identification, categorisation, and geolocation to add extra context when the information is sparse. Categorise transactions with a measurable 98% accuracy, and when merchants are identified, get them right 99% of the time. We rely on much more than broad and inconsistent merchant category codes.

Unlock revenue growth: from data to decision-ready profiles

Untapped financial data is the most underused engine for compliant revenue growth. By securely joining enriched categorisation data with your internal customer and CRM details, you create granular, decision-ready profiles that enable you to:

  • Build verified underwriting profiles: create audit-ready profiles for instant or future credit decisions, improving decision fidelity and drastically reducing manual review costs
  • Fuel customer lifetime value: power automated ‘next best actions’ for savings, investment, and debt consolidation, significantly increasing customer stickiness and lifetime value

Consumer Duty: demonstrate good outcomes

Transform your indistinguishable banking app into a hub for driving better outcomes and exceed regulatory expectations while delivering more to your customers.

Segment customers based on their their fine grain data and trigger the most appropriate personalised  journeys allowing you to cross-sell with conviction. Execute hyper-targeted, compliant product offers by accurately verifying customer needs and product suitability before the offer is ever made, mitigating regulatory risk

Prove regulatory outcomes in customer understanding, pricing, and product fit, and avoid regulatory enforcement action.

Lloyds Banking Group

“Partnering with Moneyhub will allow us to rapidly deliver far richer and more valuable insights for our customers.”

Ranil Boteju Group Chief Data and Analytics Officer at Lloyds Banking Group

Lloyds Banking Group (LBG) has selected Moneyhub to categorise and enrich all retail and non-retail transactions across LBG’s extensive customer base and brands, including Lloyds, Halifax, Scottish Widows and Bank of Scotland. This will support customers to understand what they spend their money on, and improve their personalised digital banking experiences.

FEATURE SPOTLIGHT

Four levels of granularity

Multi-level taxonomy allows for categorisation in an industry-leading four levels of detail for an even finer taxonomy breakdown.

The Moneyhub Enrichment and Categorisation Engine harnesses proprietary AI to analyse banking transaction data, categorising them into four levels of our defined Taxonomy:

  • Level 1: Category Group (e.g. Entertainment)
  • Level 2: Category (e.g. Eating Out)
  • Level 3: Merchant Category (e.g. Bakery)
  • Level 4: Loan Type, applicable to loan principles and repayments only (e.g.
    High Cost Short Term Credit)

FEATURE SPOTLIGHT

Regular transaction detection

Identify a regular series of transactions from all transaction types (both income and expenditure), beyond simply Direct Debit. Moneyhub enables this feature to help our clients:

  • determine clear trends and patterns in user behaviour
  • make nudges more relevant and timely, more likely to be actioned and build trust with customers
  • make segmentation more detailed as it looks at behaviour over time
  • use detailed cohort segmentation to improve messaging for improved cross-sell conversion