Do I need anything more? Hmm, let’s see what other people are searching for right now before I check out...
Popular Searches give hints regards the most searched terms during a specific time. Shoppers can view the queries to be inspired when they’re not entirely sure what to look for. This type of suggestion can show up even before shoppers have started entering a query or when there are no search results to show.
Spot the difference
Popular searches are the queries most used by others, designed to give hints on broad ideas or terms to start the search. Try not to confuse it with top-clicked product recommendations that direct people to specific products.
For example, before entering any query, shoppers will see a list of terms such as “long dress”, “mini skirt”, or “knit sweater”. If they select the first option, a search will launch displaying all long dresses available in your catalogue.
What’s more, Popular Searches refers to the top searches for the last day at your commerce. This doesn’t mean they’re trending terms, search terms that are becoming a trend since their popularity is increasing over the past days.
To give you a hint, you can identify popular searches mostly under labels such as top searches and trending.
Try Popular Searches to...
- Anticipate shopper intent using machine learning technology.
- Speed up query entry, especially on mobile devices.
- Improve product findability. Guide shoppers to products in your catalogue they’re unaware of.
- Enhance the shopper experience. Surprise shoppers with new ideas or alternative searches on what to look for.
The inner workings of Popular Searches
Popular Searches are based on shoppers’ actions in the search UI. As shoppers perform different searches in the commerce store, behavioral information (queries, clicks, add to cart, etc.) is collected using the Tagging microservices.
The Empathize batch process analyzes and processes the tagging information to generate popular search candidates. For example, if over the past weeks many shoppers have performed searches like "beach towel", "swimsuit", and "flip-flops", these searches are identified as valid popular search candidates. Then a review process is performed to check whether the candidates are valid according to different filters (e.g. they don't feature on a blacklist, they aren't duplicated, etc.), and eventually organize them by popularity.
After a number of days of data collection, the Empathize batch process calls the Index microservice to index the processed popular search candidates in the search engine and make them available as final popular searches.
When the shopper clicks the search box, Empathy Platform Interface X uses the Search microservice to retrieve the list of popular searches and displays them in the predictive layer, so that the shopper can start navigating the catalogue even before the search is fully typed.
The suggestion candidates from the Empathize batch process are also used for generating Query Suggestions.
For a correct performance, make sure that your current search service supports this type of feature.
Explore the interactive map to see how Popular Searches relates to the other Empathy Platform features and microservices.