Commerce website doubled conversion rate with off-the-shelf upsell model

After only a few hours contributed time, a retailer with multiple brands saw an effective upsell model built from raw sales and customer data.

man sitting at desk typing on laptop



conversion rate
increase (7% –> 12%)


leads analyzed


14 days

to revenue


The challenge

Evolve offline, outbound methods to a data-driven approach

This company’s sales team was focused on direct phone and email outreach campaigns, targeting existing leads from a large potential customer base. The sales team have multiple KPIs they were optimizing for, including overall conversion rate as well as response rate from their target list.


Upsell model fully operational in less than 14 days

Pecan’s platform ingested all raw historical sales and customer data, and built a predictive model for Upsell Indication using Pecan’s ready-to-deploy use case library. Pecan tested, validated, and deployed a full trained model in less than two weeks and by taking just a couple of hours from the stakeholder’s schedule.


12% conversion rate and potential buyers identified

With their first model, this retailer was able to achieve a 12% conversion rate—increasing their historic conversion rate by 5 percentage points. The sales team also had over 20% increase in answer rates, and were able to identify and segment potential buyers into several categories. This likelihood analysis combined with the increase in conversion rate allowed the sales team the ability focus more on top leads that were more likely to purchase, increasing sales volume and the average order value per transaction.

Want to get started with predictive analytics?