Improving Ecommerce site search is an ongoing process of implementing data-driven changes to core search algorithms. Site search is an organic thing – users are typing their search queries, basically telling you what they would like to buy. This generates loads of valuable data that you should utilize to learn and find the best algorithms and the best configuration to match those search queries with your products to maximize conversion rates.
Start by Monitoring and identifying issues.
You have to be aware of what your users are typing and how they behave afterward. There are many metrics and statistics that you can measure, but let’s focus on the two most important ones: low click-through results (CTR) queries and zero results queries.
Search queries with low CTR
Low CTR means that users searched for something, and the search returned some results, but they rarely clicked on any of the products.
What does it tell us? Obviously, there is something not right with these queries, as the results that the search retrieves are not relevant to users. The more volume a unique query has, the more money you are losing.
The second case to focus on is Search Queries returning zero results
Users search for something and get the “Sorry, we don’t have this product” result. The problem is evident here as well, and you must understand the reasons behind this because you are most likely missing on potential revenue here.
The next step is to find patterns and understand why these click-through rates or no results are happening.
- Your e-store doesn’t have these products in your supply.
- Another reason they might happen could be that you sell these products, but users cannot discover them. It is probably the case that they are using different phrasing than your search expects; thus, your search results are simply irrelevant. For example, users are typing “belt”, but your search displays such results as trousers or dresses with belts because it takes data from product title/category, wherein your product data, you have the keyword “belt”. Thus, your search engine is not able to comprehend this query properly. Your results don’t match the searcher’s intent.
One of the low-hanging fruits that you could do quickly is setting synonyms. If, after analyzing your data, you see that some of the underperforming queries are getting many hits, it’s worth doing that. There are many other actions to take, such as setting up boosts, putting redirects, modifying ranking, etc.
If you’re building your site-search in-house, you should probably get the category manager working with a development team. Just be aware that the more manual adjustments you have, the more maintenance you create for the future
Test, Analyze & Measure
Testing, analyzing, and measuring the data are essential parts of continuous search improvements. You need to monitor how the CTR is evolving for specific queries and make necessary adjustments. In some cases, changes need to be made when your catalog has changed or even based on the season. Searchspring gives the following example from one of their clients – “In the summertime, when people were typing “gloves”, they expected to see gloves related to summer sports, like bicycle gloves. And in the winter, users want to find gloves that are for skiing or snowboarding.”
When you make some significant changes in your search or launch a new algorithm, it is recommended that you conduct an A/B test.