FAQs

The search experience is very important to us, so above everything else the products recommended to buyers are those that they want.

To give buyers the most relevant products, our search and recommendation algorithms look at many factors and signals. Including the relevance, popularity, the buyer's location, language and currency and above all their intent.

Intent

To return relevant results, we first need to establish what buyers are looking for – the intent behind their query. To do this, we build language models to try to decipher how the relatively few words that you enter into the search box match up to the most useful content available.

This involves steps as seemingly simple as recognising and correcting spelling mistakes and extends to trying the sophisticated synonym system that allows us to find relevant documents even if they don't contain the exact words that were used in their exact order. For example, a buyer might have searched for 'red sneaker' but the manufacturer has written 'red trainer'. Our systems understand that the words and intent are related, and so connect buyers with the right content.

Relevance

Next, our systems analyse the content to assess whether it contains information that might be relevant to what you are looking for.

The most basic signal that information is relevant is when product content contains the same keywords as your search query. Beyond looking at keywords, our systems also analyse if the content is relevant to a query in other ways. We use aggregated and anonymised interaction data and transform that data into signals that help our machine-learning systems better estimate relevance.

Context and Settings

Information such as your location, past search history, past purchases, past organisation purchases and, currency and language settings all help us to ensure that your results are what is most useful and relevant for you at that moment.

Business Objectives

Finally, the marketplace owner is able to apply Search Rules which allow them to promote their business objectives. These business rules include; being able to pin, hide, boost, bury and filter products based on the buyers' search query, product data (e.g. product properties, supplier, stock etc.) and product metadata (AI-generated environmental score, purchase history of a product etc.).

You can connect with the platform by uploading JSONL files or by connecting via API. We strongly recommend API.

Buyers punch out to the Axiom platform via their ERP or S2P system. They then fill their basket and checkout. Once they check out, Axiom returns their basket via cXML to their ERP/S2P system where an order request is then sent to each of the suppliers who are selling at least one of the products in the basket.

Suppliers receive orders from the marketplace owner as a PO from their customer's ERP or S2P system.

Almost all languages and regional dialects are supported.

No, you just need some way of uploading and updating the information required by Axiom. This could be a product information management system, an ERP system or a spreadsheet (hopefully not though)!