AOV
Easy additions for larger baskets.
SELVE SERVE FILTERING
Filters will be applied to each possible result from top to bottom. If any candidate does not meet the filter condition it will be checked against the next filter in the list. If the candidate does not meet any filter conditions it will be skipped and the next item will be processed. Data efficiency, i.e. probable filters, is key to ordering the filters such as bicycle components to a bicycle frame.
BOLT ONS
Shorten the journey to next likely item after a customer tops up their basket.
Bundles
digiDirect implemented PA’s technology on its site in the lead-up to last November’s Black Friday sales event. While we initially believed it might take weeks or months for the algorithms to build up sufficient data to improve recommendations, we began to notice changes in customer behavior in December.
People were adding more products into their carts because of the more relevant related product recommendations, and we were getting more items per cart per sale.
This uplift of 30 per cent year-on-year has been especially pleasing as accessories tend to offer slightly higher margins.
Bundles
FEATURED IN CMO MAGAZINE
DigiDirect has subsequently seen an uplift of 30 per cent year-on-year, which Haig attributes to people “adding more products into their carts because of the more relevant related product recommendations, and we were getting more items per cart per sale.”
BOLT ONS
Leverage cross-category bought together data, or even custom application of our visual search stack to nail Complete The Look, automatically and at scale.
BOLT ONS
Improve basket mix, especially with higher margin accessories to optimize for margin mix.
Automated bundles are the lowest hanging fruit on any eCommerce website. Growing order values is great but margin efficiency from merchandiser time savings, increased units per transaction and being able to send more items per delivery is an incredible value proposition.
PA managed everything from creative design through to implementation, reporting, and even a comprehensive AB test so the team at Hotel Chocolat only had to approve widgets to go live for a massive sales uplift.
Automating bundles for Raymour & Flanigan has seen a material reduction in manual merchandising work, while driving an ongoing increase in sales impact. Sitewide revenue attribution has climbed from 1.49% to 4.7% in the first 5 months, reflecting success in early categories and incremental roll out of the technology across the site.
Co-occurence algorithms leverage item purchase data to predict which item groupings should be recommended to future visitors.
Automated bundles are the lowest hanging fruit on any eCommerce website. That is especially true of the hobbies category with users adding a great deal of bolt-on items to their cart in a never ending sequence of DIY, world-building and gift centric shopping for hobby enthusiasts through the children.
We have even found that our SKU Level Incentives products, namely Price Beat and Best Price Affirmation are actually margin accretive in spite of discounting, growing basket size and attachment rate considerably.
AI POWERED PRODUCT DISCOVERY