the key points to improve product research and provide the best results

The Importance of Search in Ecommerce

Visitors to an ecommerce site want immediate and relevant results when they search a commerce site. 68% of internet users will not return to a site if they have a bad search experience or if the search engine is too complicated! Buyers are so used to Google and its fluidity that they expect a similar experience on merchant sites. Research is also very often the starting point of the customer journey, so it has to be perfect. But providing relevant results often encounters poor quality product data.

Request an Attraqt demo

Attraqt, specialist in Product Discovery, enables brands, with catalogs of several thousand references, to present the right product to their internet users at the right time.

Even though the experience must be perfect everywhere, the search must above all be optimised. Attraqt presents 10 levers that allow us to give more impact to search results and to respond in a more relevant way to questions from internet users, in particular thanks to AI.

The purpose of these best practices? Improve the shopping experience, but also the number of conversions. Research not included represents potentially very large untapped income!

10 key points to improve internal research

Consider natural language

It is essential for ecommerce players to provide a search experience that approaches natural language. Visitors do not express themselves in “keywords”, but more and more express themselves as in human conversations, which can pose a problem in obtaining relevant results: spelling mistakes, complex sentences… Thanks to the implementation of a solution like Attraqt , AI is able to understand this natural language and provide relevant results.

When a visitor searches the Superdry brand site for ‘water-resistant men’s jackets’, they get relevant results despite searching in natural spoken language.

Suggest results in the search bar

Another practice to implement to optimize the search: the suggestion of results, also known as Instant Search. Lead buyers by suggesting search terms, products, and content. Attraqt allows suggestions of two characters entered into the search bar.

Request an Attraqt demo

Offer replacement items

Another crucial element to not lose visitors: automatically suggest suitable items for products that are out of stock or unavailable. For example, if a user searches for a bottle of “Sancerre” and it is out of stock, your search engine can understand that it is the grape variety “Sauvignon” and offer a bottle of “Sauvignon” for example. Pouilly-Fumé” instead. By displaying substitute products instead of blank results, you allow the buyer to consider alternatives and increase conversions.

Suggest synonyms

By displaying products with similar characteristics in search results, users can discover other items that they may not have thought of. Attraqt’s AI makes this task easy, so you don’t have to manually define synonyms. Specifically, it may offer products in navy, turquoise, or azure colors for a search query that includes the term “blue,” for example.

Ditto for the jargon: if a user searches for “corrugated iron nails”, the Attraqt search engine will understand that “fastening pins” and “nails” are used interchangeably and will therefore return relevant results. †

Take local specificities into account

To increase the relevance of the products you offer to visitors, you need to adjust the ranking according to regional preferences, demographics or the weather. In a marketplace, for example, AI could make it possible to offer winter tires in snowy regions or push offers for raclette machines when temperatures start to drop.

Group content and products into results

For a personalized experience, you should group products and content to be displayed together. Manuals, advice, tutorials, etc. must be shown with the related products. If an Internet user is looking for “bathroom sink” on a DIY site, it would be very helpful to also suggest the appropriate resin and a video or article on how to do the installation .

Understand the ambiguity

AI can also be of great help in enabling e-retailers to provide relevant results in ambiguous or vague searches. Indeed, AI is able to learn what buyers consider to be the closest results to their intent during ambiguous searches. When searching for “coat”, the AI ​​knows whether to offer visitors a parka, a jacket or a trench coat, depending on the buyer’s profile.


Allow multilingual search

It is important to enable your visitors to perform a search in their language, whether they are on the French, English, Spanish, etc. version of the site. Again, the goal is not to lose visitors, who will leave your site if you don’t understand the request. It often happens that the visitor confuses English terms with his language, for example he can search for “blue navy pants”, this is necessary in order to provide him with relevant results.

Integrate visual synonym search

If a visitor searches for “leather jeans”, the AI ​​can make the search engine understand that “jeans” in this case is a synonym for “trousers” and suggest other items that visually meet the same conditions, even if it is not listed in the written description of the product.

Eliminate searches with no results

It is essential to eliminate searches with no results to avoid frustration of visitors and their departure from the website. You must provide a result regardless of the search query.

Attraqt demo to improve your ecommerce site performance

Leave a Comment