Designed a new AI product for a partner-marketing platform, from a blank page to a specified build.
I designed an AI product for an affiliate-marketing platform from a blank page: how partners get matched, scored and ranked.
On top of Scaleo's affiliate-tracking platform: match the right partners automatically, catch unusual activity and fraud, and predict revenue and churn.
Scaleo · contract · scaleo.io
Context
Scaleo is a partner-marketing and affiliate-tracking platform with a large event dataset and an AI product still to define. The ask was to design that product over its existing data.
The problem
Design that AI product from a blank page — how partner matching is scored, what the analytics show, and how the predictions reach the user. All on contract.
What I did
- Defined how the system scores and ranks the best partners
- Planned the product in stages — benchmarks, unusual-activity alerts, predictions
- Set how the team would test ideas and read the results
- Owned the plan across several different types of customers
Results
- Partner-matching feature specified and queued for the engineers
- Predictions mapped out — revenue, customer drop-off, lifetime value, fraud
- Alerting for unusual activity defined across large amounts of data
- An AI-first plan the team could build against
Skills used
Product strategy, Scoring design, Analytics, Experiment design
Next
Next case: PeopleForce. If you have a similar problem, see how I work with clients, read the about page, or get in touch.