Site search engines in the ecommerce world tend to operate in isolation. They receive a query and return results. This works well until the site reaches a certain threshold. A few thresholds are:

• You can no longer improve the quality or accuracy of search results through rule changes
• When promotion and merchandising require a high level of human effort
• The popularity of certain products fluctuates so much from day to day and week to week that when business rules change, the buzz around the product ebbed.

Isolated search is problematic

When site search works without website feedback, we assume a static product catalog and unchanging buyer behavior. This is certainly not the case in most real-world stores.

Merchandisers work around this by tracking stats such as:

• Top selling products
• Latest deals
• Highest margin products
• Highest discounted products, etc.

Then merchandisers manually create promotion rules to cross-sell and up-sell the products. The underlying assumption here is that the search engine at least allows the category manager or the merchandiser to:

• Track and classify products
• Create and administer business rules
• And if you're lucky, provide a management dashboard that enhances merchandiser productivity, accuracy, and turn-around time for such requests.

However, this approach fails if you have to manage rules across many stores or categories. It breaks down further when many SKUs and products are involved. At scale, the dynamism of buying behavior and the trends in browsing and purchasing products are enormous. Transactions across the catalog vary daily, weekly or monthly, and a product relevant for a query today, is not necessarily relevant for the same query next week. In this scenario, creating a rule for every conceivable trend or product grouping is humanly impossible. Even if you could, it would take significant effort from the category manager or merchandiser.

Automated solutions achieve greater accuracy

Let's say you put in the human effort needed to build the merchandising rules for promotions, cross-selling, and up-selling based on the data you're collecting. The risk of a human creating an incorrect rule is pretty high on the scale I am talking about. Furthermore, keeping the rules updated is an even more demanding task with the variable patterns in buying and browsing behavior. It is at this point that ecommerce search must be automated to enhance the following:

• The collection of behavioral data
• Quantifying the data into metrics
• Feeding of metrics into the search system for creating merchandising rules on, on-the-fly

Insights into search behavior

Generally, behavioral data is usually thought of in relation to recommendation engines or personalized email marketing campaigns. These are truly fascinating applications but also secondary solutions to the more significant problem of ecommerce conversions. This is mainly because search remains the primary means of looking for products on the site. Therefore, even when a recommendation system aims to sell accessories to a product or sell similar products other users have purchased, it is an aside to the primary product that the visitor is searching for or has searched for in the past.

Similarly, while a personalized email marketing campaign can increase stickiness and bring back a user to make a purchase, it needs a critical mass in traffic to generate personalized data that will make an email marketing campaign effective. With behavioral targeting, the search can be used as a subliminal channel for cross-selling, up-selling, and running other marketing campaigns.

Do you want to know how site search can help you understand your customers' behaviors? Then, book a demo with Unbxd and see how it works!