Delvify AI

What Are You Looking For? An Introduction to Search

Share on facebook
Share on twitter
Share on linkedin
Share on email

Search.  A user types a word in your site’s search bar and like magic all your tagged images are displayed.  But why are you using a 21-year-old technology?  

If your user types a search query like, “that sparkly dress without the stripes that I can wear to formal event,” do you think the user will get close to the dress using a normal search bar?  Not very close is the guess we would hazard.  Most e-tailers spend enormous amounts of time, and money which are valuable resources, to tag and retag and cross tag every possible combination of words.  Yet the problems remain.  It is as if you used a scooter to get across town.  You can add a motor and maybe a small basket, but there are better ways to get to where you are going.

Many studies cited by CMSwire and other publications have shown that poor search is driving customers away.  You might think your search engine is free but the costs area hidden in lost customers.  Over 30% of customers are turned off by annoying and fruitless searches.  A whopping 70% of ecommerce search engines surveyed by Baymard couldn’t return relevant results for simple product synonyms, requiring users to type the exact keyword tagged to find the product.  This is not limited to smaller retailers.  Up to one-third of the top 50 ecommerce sites don’t allow users to search via model number or allow brand name search queries.

With these types of stats, we know that many customers are interested in your products and are leaving because of poor CX.  But, how do we know what they would do once they find the product they are looking for?  Here we have some encouraging results.  Salesforce found that visits where the shopper clicked a recommendation comprise just 7% of visits but drive an astounding 24% of orders and 26% of revenue.  If your shoppers get to the products they want, they will buy.  And this effect lasts.  37% of shoppers that clicked a recommendation during their first visit returned, compared to just 19% for shoppers that didn’t click a recommendation.  Highly engaged customers are loyal.

Baymard Institute, which provides independent research on many web related topics recently held a large-scale study of search habits and found many sites committing the same errors.  They tested many common types of behavioural searches and found problems in all of them.  All brands want to provide helpful, positive search and shopping experience to improve conversions and increase units per transaction, but few do.

Search type Graph

We can see that the beyond the three most common search behaviours, the support fell off dramatically.

 

12 Types Of Search

What are these searches and how can we improve the results?

 
  • Non product:  Users search for help pages and shipping information.
 
  • Exact:  Often users copy/paste product name such as “HT-S100F 2.0 soundbar with Bluetooth“
 
  • Compatibility:  Customers search for accessories and spare parts for products.  This is related to the “Exact” search problem.
 
  • Feature:  Users submit searches with multiple attributes hoping to narrow their search quickly.
 
  • Thematic:  Users may be thinking of themes such as “party” or “outdoors”.
 
  • Slang abbreviation and symbol:  Users have their own linguistic quirks.
 
  • Relational:  Users search for similar or “looks like” products.
 
  • Product Type:  Users often look at narrow categories like couches or dresses.
 
  • Symptom:  User look for answer to question such as, “How to clean an oven.”
 
  • Subjective:  User have emotional queries such beautiful and quality.
 
  • Implicit: (not in graph) Some users submit partial searches.
 

So, what is left?  How do we service our customers? 

 The answer is to use the most recent advances in AI.  Natural Language Processing (NLP) in particular has made all these problems easier to solve.  In an NLP search a user types their search queries in full sentences, partial phrases or lists of attributes. Any normal search engines cannot parse these advanced queries and return results.  NLP handles it with ease. 

 With Natural Language search, the search engine understands the semantic content of the users query, and can return more relevant results beyond simple keyword matching.  If done well, applying simple question filters much more quickly than dropdown boxes, sliders and checkboxes.  NLP can also help sites match iOS and Android phone speech inputs, enabling users to literally speak their queries aloud. NLP is an advanced technology, but once implemented, users simply type phrases and questions and can remove one of onsite’ s weaknesses compared with a physical store experiences.

Search remains a hot area for advances and an important way to help your customers find what they need.  Now the tools are available for optimal onsite search.

Subscribe for latest updates

Want to keep updated on the latest happenings in AI and Programmatic? Subscribe to our updates and stay in the loop

Drive your business growth today with delvify

Speak to our team to schedule a demo today