Ecommerce ops · Production

Hubo grows site search conversions 7% with SearchNode AI automation and NLP

The problem

Hubo's site search suffered from poor relevance, an inability to handle Dutch and French language nuances, and required extensive manual hardcoding that created search debt without improving core performance.

First attempt

The previous Adobe Search & Promote tool could not comprehend complex grammar rules in Dutch and French, and the manual fix approach only addressed the most frequent queries while leaving long-tail queries unoptimized, accumulating search debt.

Workflow diagram · grounded in source
1
User submits search query
trigger
“all our search terms that users were typing”
2
NLP decodes multilingual query
ai_action
“As SearchNode has sophisticated Natural Language Processing (NLP), and custom stemming algorithms, fortified with AI, we solved this challenge with ease”
3
ML algorithms rank all queries
ai_action
“SearchNode implemented automated algorithms, powered with machine learning, which optimized all queries, not only the most frequent ones”
4
Search results and filters delivered
output
“contextual and dynamic search filters optimized using mobile-first thinking”
5
Product owner prioritizes improvements
human_review
“a Hubo product owner looks through the entire list, prioritizes search improvements, and decides what will be evaluated during the sprint”
6
Monthly sprint releases new algorithms
feedback_loop
“we organize a continuous process of search improvements in monthly sprints, which can be divided into two parts, by type”
Reported outcome

After SearchNode was implemented, Hubo's site search conversions increased by 7% immediately, grew a further 4% one year later, site search usage grew by almost 10%, and CTR grew by 28%.
The search team transitioned from manual hardcoding to strategic planning.

Reported metrics
Conversions from site search vs previous solution7%
Conversions growth one year after launch4% more
Site search usage growthalmost 10%
CTR growth28%
Show all 5 reported metrics
conversions from site search vs previous solution7%
conversions growth one year after launch4% more
site search usage growthalmost 10%
CTR growth28%
manual search work eliminationleft the days of monotonous manual work behind
Reported stack
SearchNodeNLP
Source
https://www.nosto.com/case-studies/hubo/
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

After SearchNode was implemented, Hubo's site search conversions increased by 7% immediately, grew a further 4% one year later, site search usage grew by almost 10%, and CTR grew by 28%.

What tools did this team use?

SearchNode, NLP.

What results were reported?

Conversions from site search vs previous solution: 7%; Conversions growth one year after launch: 4% more; Site search usage growth: almost 10%; CTR growth: 28% (source-reported, not independently verified).

What failed first in this deployment?

The previous Adobe Search & Promote tool could not comprehend complex grammar rules in Dutch and French, and the manual fix approach only addressed the most frequent queries while leaving long-tail queries unoptimized…

How is this ecommerce ops AI workflow structured?

User submits search query → NLP decodes multilingual query → ML algorithms rank all queries → Search results and filters delivered → Product owner prioritizes improvements → Monthly sprint releases new algorithms.

Related ecommerce ops cases