Skip to content

This online publication is intellectual property of Apptus Technologies. Its contents can be duplicated in part or whole, provided that a copyright label is visibly located on each copy and the copy is used in conjunction with the product described within this document.

All information found in these documents has been compiled with utmost attention to detail. However, this does not guarantee complete accuracy. Neither Apptus Technologies nor the authors shall be held liable for possible errors or the consequences thereof.

Software and hardware descriptions cited in these documents might be registered trademarks. All trade names are subject to copyright restrictions and may be registered trademarks. Apptus Technologies essentially adheres to the manufacturer’s spelling. Names of products and trademarks appearing in this document, with or without specific notation, are likewise subject to trademark and trade protection laws and may thus fall under copyright restrictions.



Search is an important part of any e-commerce site and typically caters for visitors who are looking for something particular. These visitors tend to have a strong purchase intent which makes them a significant part of a site's sales.

The search in eSales Fashion is based on sophisticated query analysis, product lifecycle analysis, customer behavioural insights, exposure strategies, merchandising actions such as promotions or demotions, as well as business domain knowledge. All these elements, apart from the query analysis, are part of the eSales Fashion relevance arena, something which impacts a great deal more than search.

In addition, visitors are assisted in their journey through various UX details and features utilising the search functionality such as the Search Assistant and the Search Results Page.

Query analysis

The eSales Fashion query analysis is used for both search results and product suggestions, and impacts the phrase suggestions in the Search assistant. It combines basic text processing with advanced features such as concept understanding and multi-level spelling corrections to truly capture the visitors search intent.

Basic text processing

Basic text processing such as stemming, tokenisation, and normalisation are applied on all searches and content when not replaced by more advanced techniques.

Pluralisation handling

Regardless if a visitor searches for something in singular or plural form the result will be the same. Terms in a search phrase that the query analysis find to be in plural are considered to be equally valid as the singular term, so a visitor searching for dress will see the same products as when searching for dresses.

The pluralisation is treated separately from stemming and includes special handling of words that may seem like a plural version but in reality aren't, such as shorts not being the plural of short.

Multi-level spelling corrections

Spelling corrections of a search phrase are automatically performed during a search. This enables visitors to find what they are looking for even if they misspell it. In addition, the automatic corrections allow visitors to find products where the product data itself is misspelled or have spelling variations. For example, if a visitor searches for adidas and the brand name of a product is misspelled as addidas, the product with the misspelled name will be found.

The level of differentiation between the phrase and the content is furthermore something considered in the ranking, allowing relevant products not to be left out but less likely interpretations to be ranked lowered.

Concept understanding

Concepts such as what a colour is, what a shape of a product is, and how they are used together in search phrases are known to eSales Fashion. If a visitor performs a search for light blue it is more likely that they are searching for a garment in a light shade of blue, rather than a blue light, or a lightweight blue garment. Terms such as New, Sale, Discount etc. are also concepts that are easily made searchable.

Each concept has specific match types, scores, and penalties that are relevant for that specific concept. This means that the type of data that is matched determines what evaluations that will be applied to it.


A search phrase often include the colour of a product thus making colour an important concept to understand. Based on identification of colour terms in the search query and colour analysis of garments, eSales Fashion can apply colour closeness as a part of the ranking. Both how well the queried colour matches the precise nuance of a garment, as well as how much of that nuance that is present in the garment.

Colour distance
Colour distance

A visitor searching for a product of a specific colour, such as burgundy, expects to see products of that particular nuance. The definition of burgundy might however vary slightly between different customers and it is important to showcase all relevant products.

Using a colour distant measurement called CIE-distance (Commission internationale de l'éclairage), eSales Fashion is able to correctly consider the colour match criteria based on nuance of each product. This allows variations that leans slightly towards purple or lighter red to be incorporated, but lower ranked.

Colour distribution

When searching for a product in a specific colour, a visitor expects to primarily find products in that colour, not products where that colour is one of many. For example, a white and blue striped shirt has two colours. Conventionally a product like this would be tagged with the colours white and blue and appear when a visitor searches for either white shirt or blue shirt as a colour criteria is met.

Colour distribution

The more of the colour in the search phrase that is present in the product, the better the product is considered to match the colour criteria.


The product titles often hold significant information and are thus considered especially important for match ranking.

Product titles are however special in yet another aspect. They often consist of a composition of other values. For example, a title may very well be a combination of both its proper name, the product type and a color name.

Normally, a full match of an attribute is ranked higher than a partial match. Product titles are an exception to this due to the their special composition. This means that the search query shirt matches the titles shirt and Elana shirt - pink rose equally well.

Product taxonomy

To prevent misleading hits within categories with multiple product types and an & in the title, such as Scarves & Hats, eSales Fashion differentiates product taxonomies. For example, products tagged with the category Scarves & Hats do not necessarily match the term hat as it might very well be a scarf.


To avoid prefix matches that a visitor does not expect, an exact match is required when searching for sizes. For example, when searching for one piece a visitor does not expect to get all products that are available in onesize after typing one.

Phrase coverage

If a visitor is searching for a t-shirt, it does not matter if the search phrase used is t-shirt, tshirt, or t shirt. It will all return the same result. The dynamic phrase coverage ensures that not only is the queried data present in the product, but it also provides additional relevant matches.


Synonyms are used to extend searches of a phrase to include similar search phrases. For example, a synonym is used to also search for sneakers when using the search phrase shoes. Management of synonyms are made in the Synonyms tab in the Experience app.

Search behaviour driven results

The search capabilities includes the general behaviour analysis that is part in the eSales Fashion relevance arena, such as trend sensitivity. The search relevance however also includes behaviour analysis that is specific for search. Search functionality within both the search assistant and the search result will promote products that are considered especially popular for specific search phrases.

Last update: March 18, 2020