Product recommendations
Personalised recommendations online and in store from purchase and browsing behaviour.
The problem
Generic product lists ignore what each customer actually buys.
Data we need
- Purchase and browsing history
- Product catalogue
- Stock availability
How it works
- Assemble customer and product data
- Build recommendation models
- A/B test against current lists
- Respect stock and margin rules
- Monitor performance
What it changes
Targets are agreed with you before we build, and measured on your data before release.
- More relevant suggestions
- Only in-stock items recommended
- Measured through controlled tests
Machine learning
Classification, regression and clustering models trained on your operational and business data.
- Gradient boosting
- Random forests
- Clustering