15 Ecommerce Site Search Best Practices For 2020
You may think that an eCommerce site’s overall success or failure hinges on things like product selection or order fulfillment speed. But while those are important, they are nevertheless pale compared to the true backbone that power the user’s shopping experience: eCommerce site search.
And although it’s relatively simple to get an eCommerce search engine up and running, the real test is in its operation. How well does the search engine understand your visitors’ input? Does it super quickly retrieve results? How accurate are the results it displays?
We’ll walk through the leading eCommerce site search best practices, trends, and growth hacks gathered from global online retail leaders and our experience.
Ecommerce Site Search Best Practices:
- How Natural Language Processing Improves Search Accuracy And Understanding
- Data Processing Plays A Big Role In Ecommerce Search Experience
- Well Known But Sometimes Forgotten eCommerce Search Features
- Anticipating The User’s Search With Autocomplete/Autosuggest
- Accommodate Typos With Spell-Check
- Optimized For Mobile Search
- Contextual Filtering For Easier Prioritization Of Products
- Merchandising Your Search Results
- AI Assistant
- Personalized Ecommerce Site Search
- Search Performance That Can Adapt Based On Analytics Data
- Delivering Results Quickly
- Voice Search
- Image Search
- Improving Ecommerce Site Search Is A Continuous And Ongoing Process
What Is Modern Ecommerce Site Search?
Ecommerce has fundamentally transformed the way we shop. With new technologies being continuously introduced, users get pickier and pickier on what they expect from online retailers. And oh boy, they expect a lot – recent Forrester study showed that 8 out of 10 users LEAVE the online store if it failed to provide its’ customer with convenient website navigation, relevant search, or clear product information. Most likely, they will never come back.
Let’s face it once and for all – eCommerce search is not easy. It’s naive to expect that the simple search integration will do a good job. If you wish to create enjoyable online shopping experiences that generate an ongoing revenue stream, it’s not enough to have a simple keyword-based generic search engine with simple features.
Modern eCommerce site search goes beyond the search box. A genuinely effective search solution should include such features, as navigation (dynamic filters and facets), intelligent autocomplete suggestions, NLP and custom stemming algorithms, advanced analytics, and dashboard, proactive search assistance, personalization, A/B testing, not to mention smart ranking and data relevance algorithms, enriched with artificial intelligence, and machine learning, to continually study your users’ behavior, and to automate and remove the need of manual labor – and that’s not the end of the list, we could go on for hours.
Even more, great features and technologies are just the first part of a modern eCommerce site search solution – if you desire to see growth in results from your search engine, you need to be always working on it. It’s not enough to integrate a site search engine – once you stop improving it, you will see the quality of search (and your conversions) drop.
Why Is Ecommerce Site Search So Important?
When you are building (or working on) an eCommerce business, there is so much technology and features to invest in, thus naturally, you may think is it really worth investing time and money in your onsite search? Well, any features and new technologies are great, but they should generate sales first and foremost. And eCommerce site search could be that money-making machine.
Don’t believe us? Let’s look into numbers:
- Research shows, that site search functionality is used by 1/3 of ALL online store visitors
- Don’t forget, that visitors, who use search, are coming with clear intent – they have conversion probability up to 6 times higher
- Based on SearchNode internal data, searchers generate ~30-60% of ALL eCommerce site revenues!
Features and new technologies are great, but they should generate sales. When making decisions, data helps a lot. The very first primary data to cheWe highly recommend analyzing your situation before making any decision about search. As always, in the decision-making process, data helps a lot. For eCommerce, the most critical data usually can be retrieved from Google Analytics. The very first primary data to check:
- % of site visits used the site search
- % of site transactions/revenue coming from those visitors
- An average conversion rate of the site
- An average conversion rate of those that use the site search
Now you can see how much of your total revenue comes from users who use search. UsuNow you can see how much of your total revenue comes from users who use search. Usually, it’s a surprise for online retailers who didn’t know these numbers before. Although every business is different, however, these are the prevailing trends in eCommerce search statistics, that we already mentioned:
- Around 30% of site sessions are with site search usage. It’s perfectly normal if this metric fluctuates around 10%-30%. But if less than 10% of site visitors use search, this might be affected by such things as a too-small search box, terrible search experience, or your business model where product discovery is accessible without a search. If this is the case, you should first figure out the reason why less than 10% of your sessions come from site search, and only then try to improve your onsite search.
- Conversion rate of sessions with site search is usually 6x higher than conversion rate of the site, even with a very mediocre search experience. Just imagine how much difference an excellent onsite search experience can make!
- 30%-60% of site transactions usually come from sessions with the site search. What a money-making machine your search is or could be, huh?
But on the other side of the spectrum, people are using their natural language and vocabulary when searching, and many eCommerce search engines still aren’t returning the results people want.
To understand where your search struggles and what improvements should be done, keep an eye on these metrics:
- Search queries with low CTR. You will identify queries that users type in the search box, but don’t click on retrieved search results. Pro tip: don’t focus just on the top 100 most frequent search queries; all low hanging fruits are in the long-tail.
- Search queries with “next page” clicks. You will identify queries, that users type, and in the search results page, go to the 2nd page. They probably didn’t find desired products on the 1st page, meaning that your eCommerce search engine failed to provide relevant enough results
- Search queries with no results. You will identify queries that don’t retrieve any results at all…
To have a process of continuous search improvements, implement a routine to check these metrics at least once per week to always be up to date, and understand the weaknesses of your onsite search. This is the most crucial of all eCommerce site search best practices.
Now that you have a clearer picture of how site search can make or break your eCommerce website, the next question becomes — what can you do about it?
How to Improve Ecommerce Site Search – Best Practices With Recent Trends And Examples
Whether you’re displeased or disappointed by the state of your current search, or you’re in the market for an eCommerce search engine that ticks all the right conversion boxes, here are the features and best practices you’ll want to look for:
1. How Natural Language Processing Improves Search Accuracy and Understanding
Natural language search, also called NLP or natural language processing is the ability of a computer program to understand human speech as it is spoken. The most common uses of this technology are when you tell Amazon’s Alexa to play a song or ask Siri to call someone from your contact list.
But the field is wide open in terms of its potential. With regard to site search, NLP can be used to not only extract valuable data on consumer searches, but it can also be used to more accurately target results based on what isn’t said, in addition to what is.
Here, accuracy is of vital importance. But searches can become much more complex thanks to the nuances of language. Ideally, the eCommerce site search solution should be able to understand and differentiate between a wide variety of queries.
Below are a few of the many different results such an algorithm must juggle:
Item + attribute queries
In the example below, Farfetch.com seamlessly retrieves search results based on an item + attribute query, such as women’s shoes, even though products’ titles don’t have these keywords.
Products are relevant, not mixed with accessories or other irrelevant but related products:
Singular and plural queries
Another example, from our client ConsigliosKitchenware.com, shows how eCommerce site search engine should effortlessly adapt to both singular and plural forms of a product search:
But this is just one, relatively simple, example.
A truly intelligent site search engine needs to understand the complexities and nuances between multiple languages, including grammar rules and structure
At Sportguru.ro, a search for a bag (geanta in Romanian) and bags (genti) needAt Sportguru.ro, a search for a bag (geanta in Romanian) and bags (genti) needs to return the same results regardless of whether the term used was singular or plural. And it’s done automatically by algorithms, without any manual human touch:
Compound words for German and Dutch languages
These languages are complicated, and search engines often struggle to understand the user’s intent. A great example from our client Hubo.be: user searches for boor machine (drill) and finds relevant results like klopboorschroefmachine (also a drill), which is a compound word made from 4 words: klop boor schroef machine.
2. Data Processing Plays A Big Role In Ecommerce Search
Ecommerce websites have lots of searchable data: titles, descriptions, categories, attributes, reviews, internal rankings, etc. It helps the eCommerce search engine to find relevant results. However, the data should be well processed and prepared, not just indexed with the search engine.
Some of the data processing best practices from eCommerce leaders and SearchNode:
- Converting messy or poorly structured data into the organized structure by identifying patterns
- Automating processes, so there is no human touch needed. Advanced data processing should work by itself 24/7 with any products
- Cleaning, tagging, extracting, and optimizing data so well, that search will understand even long-tail complex queries. E.g., Asus 16gb ram gaming laptop for teenagers
Let us give you one real-life example of great data processing advantage:
The ability to handle long and complex search queries
In the example below from Bestbuy.com, we performed a sophisticated search for “lenovo 16gb ram laptops for business”. With mediocre search solution, we’d be given results that include desktop computers with 16 GB of ram, or laptops which aren’t Lenovo brand or those who don’t have 16 GB ram.
Here, the site search was smart enough to return matches that included the brand name, the specified amount of memory which is technically RAM, even a label “Great for Business” and all laptops, demonstrating the search engine’s ability to juggle multiple specifications from different data fields easily.
Relevant matching: is it an attribute or the product that user is searching for?
When the products’ data is indexed without advanced processing, bad things could happen. Here is the example from a great company Vinted but not so great search experience (which I believe they are working on!).
The user searches for a belt and finds products like dresses, trousers, or pants with a belt. The search engine didn’t distinguish belts from other products that have belts as an attribute which is a bad search experience:
3. Well Known But Sometimes Forgotten Ecommerce Search Features
Ecommerce site search appeared together with the first online stores in the 90s. Some of the functionality is known for years, but online retailers sometimes forget them or even misuse them.
Distinguish between synonyms
In this example, from Zalando.co.uk, a user searches for a dark bomber and finds dark products: oil grey, black, blue, navy, and so on. Although keyword dark is not mentioned in the title, nor in the product page (I checked it myself), results are relevant.
This could be achieved in many different ways, from AI image recognition algorithm, which can tell the color to manual synonyms adding.
Although we are not big fans of manual synonyms adding in such cases, it’s still an option for online retailers to improve their internal search.
Transliteration to and from other alphabets
Conducting a search for a sportivnaja sumka (sports bag) on Latvian eCommerce website 220.lv allows for transliteration both to and from Russian (Cyrillic) and Roman alphabets.
Addressing this common behavior in different regions like Russia (Cyrillic) or Greece (Greeklish) allow users to use their natural writing language, find relevant products fast, and convert at the highest rates.
4. Anticipating The User’s Search with Autocomplete/Autosuggest
When you have hundreds, or even thousands of products, being able to anticipate the user’s query before they finish typing saves time and gets them to the right product faster.
Autocomplete can help. By anticipating and serving products as the user types, they’ll be able to find precisely what they need rather than slogging through page after page of results.
Here, we look to the leading search and eCommerce companies for inspiration.
If you can give your users an autocomplete search experience similar to Google or Amazon, they’ll immediately feel familiar with and accustomed to searching your site.
Once the target keyword(s) are auto-completed, the system should then recommend products accordingly. This leads to a very high conversion rate, as you’ve just matched the user’s query in seconds, rather than forcing them to scroll through countless results.
And if you need specific customization work done with regard to your own brand of products or other particular features, your eCommerce search solution should allow for this capability, not simply leave you feeling “stuck” with the default parameters.
A great autocomplete example by our client Castorama.pl with highlighted 4 main discovery sections: main keyword in different categories, keyword suggestions, product suggestions, and inspirational articles. What a highly converting experience!
5. Accommodate Typos With Spell-Check
Despite the user’s best efforts, sometimes typos can happen. This is particularly true concerning brand names. Even if you carry a specific brand, the results may not show for your user if there’s a spelling error.
By enabling a robust spell-check, your site search engine can correct the user as they type to maximize the chances that they’ll get the result they want.
6. Optimized For Mobile Search
Mobile search is nothing like desktop search, and trying to squeeze all that information into a tiny screen is only causing your users endless frustration.
Because consumers are limited by a small screen and tactile search and filtering, the best mobile search experience has to be built with these requirements in mind. Having a large, prominent search box, together with relevant auto-complete and rapid return of results, can make an incredible difference in the user’s shopping and search experience.
7. Contextual Filtering For Easier Prioritization Of Products
When you have dozens or even hundreds of relevant search results, how do you expect the user to sift through them all? With contextual filtering, you give the user control over their search experience, letting them adjust various attributes like price range, size, brand, and so on, to narrow down their ideal result with laser-like focus.
A great example from BestBuy: when a user searches for a gaming laptop, filters are contextual to this specific search query; but when a user searches for a fridge, filters now are different, again based on this particular search query.
Not only does this provide the user with far greater flexibility, but it also greatly increases the probability of a sale
8. Merchandising Your Search Results
Although some form of onsite search is often built into eCommerce and shopping cart platforms, many retailers choose not to use it because there’s a noticeable lack of merchandising options for the results that are returned. Ecommerce website owners often cannot change the order of products displayed or filter out certain categories, making the search results page more of an “all or nothing” decision.
Fortunately, it doesn’t have to be that way. New, innovative technologies are available in eCommerce site search tools that allow for proper “searchandising” — that is, provide online retailers with the ability to give different “weights” to various products and their attributes so that they have more precise control over which results are displayed, and when.
For example, the best site search engines for eCommerce allow you to assign certain categories to be displayed first based on the criteria you select, including number of sales, click-through rate of the products, stock updates, trending products, and more. All of this information can be determined with AI algorithms. You can choose to show specific items that match all relevant queries, so that particularly popular, trendy or seasonal items appear first.
Most “out of the box” site search engine solutions will consult with eCommerce retailers from a technical and implementation standpoint, but only few will venture into consulting with them based on their “searchandising” potential. This is where working with a smart, dedicated enterprise-grade eCommerce search provider can make all the difference.
Properly merchandising your search results will also allow you to show recommended items even if you don’t have any exact matches for the user’s query. In this way, you not only deliver improved search results, but you also generate more sales and greater exposure of the types of products you want to promote.
9. AI Assistant
Artificial intelligence has come a long way in recent years, and with these great strides, it has reached the potential to learn from and capitalize on the user’s search itself, but the intent behind that search.
In the example below, we found 3 relevant results. If a typical user sees this, he might not want any of the retrieved results for whatever reason. This is where most eCommerce search engines would stop. But it’s understood that he has a high intent to buy, so why let him go so easily?
Instead, your site search should be proactive. This isn’t to say that it should be mindlessly filling up the page with irrelevant results, but it should understand enough to be able to provide similar results — hypothetically, i9 notebooks that may not be Dell, for example.
10. Personalized Ecommerce Site Search
Being able to personalize search results based on a user’s browsing history, level of interest in a product, and other factors can greatly help improve your site’s conversion rate. It is the modern-day digital version of your own personal shopper.
For example, if a user has been browsing through an eCommerce site and looking over product pages for Samsung smartphones, their subsequent search results would catch this search trend and boost the results for the Samsung smartphones, thus increasing the probability that the user will ultimately buy.
11. Search Performance That Can Adapt Based On Analytics Data
Only 7% of companies report they’re efficiently learning from onsite site search data & using that in other areas of their business.
This means that there’s a lot in the way of potential revenue, improved customer retention, and brand loyalty left untapped. By properly understanding and leveraging site search data and learning how to apply it to other areas of your site and your business, you’ll be setting yourself up for exponential levels of success.
However, the search performance shouldn’t be an end-goal. Instead, it should be something that is consistently updated and adapted based on search performance, popularity, and trends.
As you no doubt know, fidget spinners were hugely popular with kids and teens. But many eCommerce businesses missed out on this trend because they assumed that nobody would search for or buy this item from a website.
But there were some savvy businesses who capitalized on this trend by analyzing their search stats and seeing the trend for fidget spinners grow. They saw an opportunity and pounced on it.
And fidget spinners are just one of many examples. This same pattern repeats itself again and again as more products achieve a sudden and incredible spike in activity. Smart, adaptive eCommerce site search tools can track and monitor this, uncovering unconventional “gold nuggets” like fidget spinners that could be poised to explode in popularity.
12. Delivering Results Quickly
Finally, the delivery of these results needs to happen almost instantaneously. Users don’t have the time or the inclination to wait for the AI to crunch all the variables and adjust all the results. And if your site search takes too long, no matter how relevant the results may be, people will simply go elsewhere.
13. Voice Search
Voice Search is a big thing but not really related to eCommerce site search.
It mostly happens when a person communicates with the device, i.e., Alexa, Siri, Cortana, but not when a person is discovering and researching products in the eCommerce site.
Let’s take this Cortana video example to feel the pattern of voice search usage.
SearchNode offers a voice search feature, and various clients have implemented it, but the usage across all clients is only 0.3% of all the searches done. Other metrics like CTR, add-to-cart rate, or conversion rate, are identical. The majority of search queries are the same types as in textual searches. Therefore it’s only a nice to have feature but not a game-changer.
Voice search could be a game-changer for SEO purposes to get more quality traffic. ConversionXL wrote a great article on how eCommerce companies can compete with Alexa and why voice search is important for B2B eCommerce.
14. Image Search
Seeing something once is better than hearing about it many times. Seeing something once is better than hearing about it many times. However, sometimes, we write keywords in a search box to describe something we saw or imagined. There are several areas where images could help users find products easier:
Reverse image search
Just make a photo or a screenshot and find similar products. Reverse image search is relevant when the products are difficult to describe or related a lot to a visual appearance like clothing or furniture.
Ebay is doing a great job enabling their users searching by images. They have made an excellent use-case video from them.
More attributes from images
Image analysis could be beneficial for enriching products’ data. AI technologies like Google Vision API extracts attributes that could be used for a textual search.
When an online retailer sells tens or hundreds of thousands of products, this is a scalable way to utilize an image for enriching textual product data. It will help the eCommerce site search get more data to search in. Just make sure the data is well processed, so it would improve relevancy, not decrease it.
Search refinement by visual form
“Round but not to round, cowboy-style but not Silverbelly….” – sometimes it’s just impossible to describe what you are looking for, even to yourself. AI image objection recognition helps users select filters from visual forms.
In the example below by Vestig.io demo store, hats have a visual form filter that users can click and get the exact shape products, instead of textually described hat types.
QR in-store codes for omnichannel search experience
QR codes are used widely in the retail industry. They help digitalize the whole industry. I.e., ~1.3 billion mobile QR code coupons were redeemed last year, and the number is expected to rise to 5.3 billion by 2022 from 1 billion devices, according to a study from Juniper Research.
But how can QR In-Store codes help physical store’s visitors and eCommerce search?
One of the reasons why people visit a physical store is to see and touch a product in real life. After a real-life examination, they decide if they want to order a product or not. If the product didn’t fulfill their expectations, they might explore other similar products because they are already in-store. Afterward, if they did, they either purchase it in a physical store or online.
When there is a QR code that leads directly to a product page in an online store, the user skips many steps like writing product code or name into a search box and trying to find which one is this specific product. Also, probably the most significant advantage is that retailer can easily measure purchases which have been done online from the physical store. A true omnichannel experience.
This behavior is noticed with retailers who sell visually important products like furniture, fashion products, art, non-traditional products, and so on.
15. Improving Ecommerce Site Search Is A Continuous And Ongoing Process
We can’t stress this enough – site search needs to be continuously improved. Your online store visitors, using search organically, generate so much data for you. Your job is to make this data an advantage.
What’s important is to set up the correct processes for that. If you want to achieve scale on your improvements, you should make them on an algorithmic level, not just add some synonyms/redirects manually. We are talking about the continuous search improvements process here.
Continuous search improvements – is an ongoing systemized process of improving site search in a scalable way by implementing data-driven changes to core search algorithms.
By always experimenting with new data-driven hypotheses and making algorithmic improvements, you will achieve scale, and your conversions will rise significantly. We created a full four steps plan for continuous search improvements – feel free to use it.
Any provider can offer an “off-the-shelf” eCommerce site search solution, but how often is the company actually there for you once the implementation is done? With the full range of products and services that can be sold online, you need an enterprise-level site search solution that can be fully customized – not just in terms of design best practices or integrations, but in overall resource planning and algorithmic updates. You need a solution that can provide you with a completely tailored system built to incorporate all of these points
We made this overview of the possible options for online retailers to build and continuously improve eCommerce site search solutions, to help you find the most suitable one:
- In-House with Elasticsearch or Solr
- SaaS Vendor
- The Rise of the Hybrid: SaaS + Search Solution Developers
Does Your Ecommerce Site Search Do All of This?
Integrating these eCommerce site search best practices can seem overwhelming, but the payoff in terms of improved customer experience, greater customer retention, and overall brand loyalty is amazing.
These points and examples illustrate the many ways that your eCommerce site search can be improved to more accurately retrieve and present relevant results in a rich, engaging atmosphere.
If you’d like to see how your site search is performing and whether or not you’re giving your customers the best possible search experience on your eCommerce site, click here to get your FREE eCommerce search analysis, conducted by Search Experts.
This detailed site search analysis will be performed individually for you by a dedicated eCommerce search expert. The report is designed to help you understand where users may be falling out of your funnel and help you reach and retain more customers through a smart, powerful on-site search solution.