 Excellent control and maintenance of synonyms is a surefire way to improve the relevancy of your ecommerce search. Now, Findify has made the creation process quicker and easier than ever before - with the creation of a new Bulk Upload of Synonyms capability. In the world of ecommerce, site search is everything. An effective search functionality is often the only difference between a sale and a lost customer - if shoppers can’t find what they’re looking for, they don’t have the opportunity to buy it. One aspect of a truly hard-working site search lies in the engine’s synonyms capability. What is a Synonym? A synonym is a word or phrase that means exactly or nearly the same as another word or phrase in the same language. For ecommerce merchants, a synonym capability is a useful tool for improving the product search relevancy. Take, for example, a furniture store. A shopper goes to the store’s website and searches for ‘couches’... and no couches are shown. Why? Because the store lists their couches as ‘sofas’ and the term is not used in any other underlying data. In this case, the merchant would create a two-way synonym to increase their shoppers’ search relevancy. If you tell the software couch = sofa (and vice versa) then shoppers can search for either term (whichever is most popular within their own vernacular) and their search will still return relevant results. In other situations, a one-way synonym might be more appropriate. For example, in an electronics store where you might want a search for ‘Phone’ to return Apple models (among others), but you don’t necessarily want a search for ‘Apple’ to return phones of other makes and models. Here, you would create a one-way synonym, denoting that phone = apple but NOT vice versa. A third use case occurs when you would use synonym control for tactical purposes. Let’s say, for example, you see in the analytics that a lot of shoppers are coming to your fashion store and searching for pregnancy clothes - a search which returns zero results. While you don’t have a pregnancy line, and you don’t want to create one, a merchant could in this case create a one-way synonym, telling the system pregnancy = stretchy. Then when shoppers search for pregnancy, they will see your stretchy leggings and tops, which they might be interested in. Bulk Upload of Synonyms Findify has recently improved the way in which ecommerce merchants can create and add to their store’s synonyms dictionary. Now, while merchants retain the option to create synonyms manually, they can also choose to upload a file with synonyms they have already created elsewhere. This saves time for the merchant should they happen to already have a long list of synonyms they already use. Merchants can bulk upload either one-way or two-way synonyms. To do this, go to your Findify Merchant Dashboard and navigate to either Search > One-Way Synonyms or Search > Two-Way Synonyms.  Synonyms must be uploaded in a CSV file with one column. Synonym groups should be separated by rows while synonyms within groups should be separated by commas.  For more information on Findify’s powerful ecommerce tools, including personalization software and solutions such as Personalized Search, Smart Collections, and Recommendations, book a demo here.
To read more about synonyms within Findify, including the difference between one-way and two-way synonyms, click here. 
This brand new feature boosts conversion rates for ecommerce merchants by improving UX for shoppers who conduct searches for makes, models, and SKU numbers.
The latest feature released by Findify developers sees the leading Site Search and Personalization software company improve its Personalized Search function even further - this time with improved model search functionality to help shoppers quickly and easily find (and buy!) the products they are looking for.
What is model search, and who uses it?
A model search, also referred to as a SKU search, takes place when a shopper types a product number/product code into the search bar of an ecommerce store.
This search could be written in the form of ‘Product + Model’ along the lines of ‘Iphone 11’, ‘Sony A6000’, or ‘Fujifilm X-T3’, or it could take the more ambiguous form of something like ‘rt9027483’. Merchants most likely to see customers searching using SKU-style parameters are largely those selling cameras, laptops, parts, mobiles, gaming equipment, automotives, and home electronics. 
An example of model search in action for Findify client Cyberphoto. The search term ‘nikon d5’ now includes Nikon D500 and D5000 - a full range not available through purely tokenized engines.
How hard is it to build an effective search solution for SKUs?
While getting this type of search right is extremely difficult, it’s well worth the effort. Those searching for products in this way usually know exactly the make and model they want to buy, or at least the exact product range they want, meaning they are shoppers with a very high purchase intent and are, therefore, particularly valuable visitors.
The issue, however, is that a model search is notoriously hard to perfect. “For normal, word-based searches, we’ve built a system, based on Tokenization, where shoppers don’t need to type out the entire word, or to even type their query correctly, and they will still get relevant results,” explained Findify’s Seva Goloviznin. “But model search/SKU searches need to be treated differently. While tokenization is great for word-based searches, there are limitations to this method when applied to model search and SKU search. Up until now, this has meant that shoppers who wanted to search using an SKU had to type their query in perfectly to get the product they wanted to find.” Of course, it isn’t always possible for shoppers to input the SKU exactly right, and merchants shouldn’t expect them to. Perhaps the shopper doesn’t know the full SKU, or they don’t realize there’s a hyphen or space in it… or they simply don’t want to spend time writing the full string. Let’s say, for example, there is a product called an ‘X-1/1’. Shoppers can, and will, search for this in the following ways ‘X-1/1’, ‘X1/1’, ‘X11’, ‘X1’, ‘X-11’, ‘11’, ‘X’. If these searches don’t yield relevant search results, the shopper is at a high risk of churning and taking their business elsewhere, assuming the store doesn’t have what they’re looking for. In other cases, more related to discovery, some shoppers might just want to see all the products in a certain range, so they want to type ‘T5’ and view not only the Lenovo ThinkPad T560 but also the T550 and the T540p.  So what’s the solution?
Up until now, the best solution has been to tokenize the search results. So, in accordance with our previous example, ‘T’ becomes one token, and ‘560’ becomes another token. Longer SKUs would also have subtokens. When a user enters a query, a collection of documents containing these tokens are searched for the best matches.
While this system can work well, it has limitations. Firstly, it is a huge undertaking to create so many tokens, and secondly it creates a large amount of data for our system to process, meaning it will likely take a slightly longer time for search results to populate. Other ecommerce site search providers have attempted to solve this problem with prefix search, however Findify developers quickly realized this was just switching one set of problems for another - this “fix” decreases both precision as well as the overall site experience. This is why Findify developers have implemented a new system, utilizing border-ngrams. This method means there is no need to create an endless amount of tokens, and also means searches take less time as there is less data to screen. The icing on the cake is that Findify’s border-ngram method also makes model search results a lot more relevant. 
With Findify’s model search, queries for ‘microsd’ yield a full range of results, including close ranges of products like microsdx, microsdxc etc.
What is a border-ngram and how is it used?
Put simply, an ngram is a type of probabilistic language method for predicting the next item in a sequence. However a full ngram generation may quickly explode index size, slowing the search down.
A border-ngram, therefore, is a compromise between sensitivity and index size, ensuring relevant results are returned without generating a huge amount of data and adversely impacting speed. Uniquely utilizing this method, Findify’s now improved search solution ensures that whenever a shopper types a search query that contains both letters and numbers, the system will recognize this as a potential model search, activating the border-ngram. This ensures that customers opting for a SKU search will always find exactly what they’re looking for, regardless of misspellings, benefitting both the shopper and the merchant alike. For more information on Findify’s powerful ecommerce tools, including personalization software and solutions such as Personalized Search, Smart Collections, and Recommendations, book a demo here. 
New one-way synonym capabilities are set to make shoppers’ search results even more relevant - helping merchants increase revenue and reduce churn.
In the world of ecommerce, site search is everything. An effective search functionality is often the only difference between a sale and a lost customer - if shoppers can’t find what they’re looking for, they don’t have the opportunity to buy it.
One aspect of a truly hard-working site search lies in the engine’s synonyms capability. Two-way synonyms are good...
Take, for example, a furniture store. A shopper goes to the store’s website and searches for ‘couches’... and no couches are shown. Why? Because the store lists their couches as ‘sofas’.
Likewise for electronic stores and ‘multi-function’ vs ‘all-in-one’ printers, and retail stores battling with ‘pants’ vs ‘trousers’ and ‘t-shirts’ vs ‘tees’.
This functionality may seem simplistic, but a recent study shows the site search of more than 70% of online stores don’t feature proper synonym capabilities. Findify, a leading provider of site search and personalization solutions, includes synonym capabilities at the core of it’s search AI-powered engine, and has newly improved this offering to go one step further with the introduction of one-way synonyms. An example of a regular synonym, also called a two-way synonym, means that ‘pants’ = ‘trousers’ and, therefore, ‘trousers’ = ‘pants’. A search for either query will always return the other also. While this is essential and is, apparently, more than what 61% of ecommerce stores currently feature, the next level of this is a one-way synonym for use in situations where term one equals term two… but term two doesn’t equal term one. ...but one-way synonyms are even greater
In an electronics store, for example, someone searching for ‘phone’ should also see results like ‘Google Pixel’ and ‘Samsung S10’. However, someone searching for ‘Samsung S10’ does not want to see phones of other makes and models.
Likewise, in fashion, a search for ‘summer clothes’ should return results like ‘dresses’, ‘skirts’, and ‘t-shirts’, however you don’t want a search for ‘dresses’ to return skirts or t-shirts, or any results that are not actually dresses. In general, one-way synonyms are usually used on more generic terms in order for shoppers to find items that have been given quite specific titles and descriptions. This means search results are more relevant for the customer who, if finding what they were looking for, is more likely to make a purchase. Managing synonyms within the Findify dashboard
Merchants can control their site’s new and improved synonym capabilities via the Findify Merchant Dashboard.
First, click on ‘Search’. Then, included in the menu on the left, you will see both ‘One-way synonyms’ and ‘Two-way synonyms’. In the field provided, write what word you would like to create a synonym for, and then write the desired synonym in the corresponding field. Hit ‘Save’ and your synonym will appear in the below list of ‘Synonym Groups’. While the synonym is now created, merchants need to push the changes live on their site. This is easily done by migrating back to the homepage of the Findify Merchant Dashboard, and then clicking on ‘Sync, Status & Usage’. Then, in the left-hand-side menu, select ‘Product Sync’ and hit the blue ‘Sync Products’ button.
For more information on Findify’s powerful ecommerce tools, including personalization software and solutions such as Personalized Search, Smart Collections, and Recommendations, book a demo here.
Read more news about our productExperience the Findify effect
This brand new feature makes it easier for online shoppers to find the products they are looking for - also when searching using numerical SKU-style parameters.
The latest feature released by Findify developers sees the leading Site Search and Personalization software company improve its Personalized Search function even further - this time with improved numerical search functionality. As the most popular Findify solution, with an algorithm powered by the latest in AI and machine-learning developments, the company’s Search solution is constantly being improved, tweaked, and optimized - for the benefit of all merchants using the valuable ecommerce tool to increase revenue, boost conversion, and improve the overall user experience on their website. The new numerical search functionality now encompasses SKU-style look-ups. What is an SKU and how can Findify help customers who search for them?
A Stock Keeping Unit, or SKU, is a unique code that is assigned to a product to identify it, and helps merchants keep track of inventory.
To give an example, a paperback edition of the first book in the Lord of The Rings Trilogy could have this SKU: LOTR-1-PB. Things get a little more complicated, however, when searching for items with similar, or complicated, SKUs. Take computer gaming company Nvidia for example. The company could have a product with the SKU of: Nvidia gfx1080. “Previously, Findify search would take this term and treat it like a word, meaning searching just for ‘gfx’ or just for ‘1080’ wouldn’t find the product,” explained Anders Gullander, Findify Head of Product. “Now, we split it into parts, so that it’s easier to search, improving our text analyzer to break down these SKU-style strings. Searching just for ‘gfx’ will find all products with gfx in it, including ‘Nvidia gfx1080’ and ‘Nvidia gfx960’ etc. Searching for ‘gfx1080’ or ‘gfx 1080’ will show exact match products first, followed by partial matches. If there are no exact matches it will fall back to the usual expanded search, as it did before.” 
An example of numeric search functionality on the website of Findify client Shopping Express.
While this new functionality may seem basic, it is actually quite a complicated matter behind the scenes.
Mr Gullander explained there is a lot of complexity involved in breaking down not only words, but also numbers, and teaching the system to understand the endless ways and combinations that a product title could be written into a search bar. After extensive testing of the new feature, which involved invaluable feedback from merchants, the experts at Findify have reported this improved numeric search feature greatly improves the search functionality for shoppers conducting SKU-style searches. “This is a really great new feature, which I think a lot of merchants, and online shoppers, are going to benefit from. Our customers that are already using it see a great improvement,” said Mr Gullander. “We have a lot of big projects in the works at the moment, but it’s great to still have the capacity to roll out these smaller, but extremely useful, features which will help our clients to continue to sell more online.” For more information on Findify’s powerful ecommerce tools, including personalization software and solutions such as Personalized Search, Smart Collections, and Recommendations, book a demo here. Read our most recent product updatesCheck out the latest Findify clientsExperience the Findify effect |
Discover more how Findify can improve your salesRequest a demo
CategoriesAnalytics Collections Interface Jetshop Linguistics Merchandising Neto Recommendations Search Shopify Sync Technical Support |
|