Turn your transaction data into new revenue
Spade’s transaction foundation model predicts what is most relevant to each customer from how they actually spend, so you can offer the right card, account, loan, or reward at the right moment.
- Personalization at scale
- Offers customers want
- Growth in cards, deposits, and loans
- Lower cost per account
- Personalization at scale
- Offers customers want
- Growth in cards, deposits, and loans
- Lower cost per account
Where your customers spend shows which offers fit them and which products they will need next. Predictions helps you understand each one and serve them individually, across every channel.
Know who to reach, with what, and when
Predictions learns what each customer’s spending says about them from the verified merchant behind every transaction, so every customer sees the offers most relevant to them and the products they are likely to need.
Find who is ready for the next product
See which customers are likely to want a credit card, a mortgage, or a student loan, so each offer reaches someone it fits.
Know which segment each customer belongs to
Predict each customer’s segment from how they actually spend.
Personalize every offer
Predict which merchants each customer is likeliest to visit next, so the offers and rewards they see are ones they will use.
Spot risky users early
Flag merchants and users engaging in fraud, investigate them sooner, and reduce fraud losses.
Predictions in action
Fine-tuned for a US bank’s lending program, Spade’s foundation model outperformed a traditional propensity model built for the same task by 35%.
0%0% Better than a traditional propensity model
Spade’s ring analysis replayed eight months of a card issuer’s transactions. Of all the fraudulent spend that cleared in that time, Spade would have flagged the merchants early enough for the issuer to block up to $3 million of it.
Up to $0MUp to $0M Of fraudulent spend flagged early enough to block
Three ways to use it
Run the model as it stands, with no data science team required.
Have Spade fine-tune the model for the outcome you care about.
Use Spade’s software, infrastructure, and embeddings to train a model of your own.
A model built to understand both sides of every transaction
- The business
Learns what each business is
From Spade’s own verified record of it, rather than from the payment message.
The customerLearns what a customer’s spending says about them
By reading their history with the verified merchant attached to every transaction.
Spade never receives personally identifiable information, and a model tuned for one institution runs on that institution’s own customer identifiers.
Powered by Spade’s Merchant Graph
The Merchant Graph is Spade’s verified record of 99.9% of US and Canadian businesses and how they relate: every location to its brand and owner, every business to the ones most like it, and what spending at each one says about the person who spent. Because it knows how businesses relate, a model built on it can tell which businesses are alike.
99.9%
of US and Canadian businesses, including the long tail
>99%
accuracy, checked against the verified record
Rich
location, brand, category, and attributes for every business
Connected
every location to its brand, every brand to its owner
