<img height="1" width="1" style="display:none" src="https://q.quora.com/_/ad/ad9bc6b5b2de42fb9d7cd993ebb80066/pixel?tag=ViewContent&amp;noscript=1">
The Loop54 Search Algorithm

From Topic Modelling to Neural Networks

 

Evolution of the Loop54 algorithm

 

Algorithm version Context model Description

Topic Modeling.png

Topic Model
(2012)

Topic Modelling 

Determined underlying structure by clustering words that are used in the same context. Created initial ability to find Related Results.

 Batman New.pngBatman
(Q2 2013)

Behaviour Augmented Topic Model and Association Network (Topic Modelling) 

Added the inherent product structure to reinforce topic models. Improved contextual word clustering. Added behaviour-based learning, faceting, initial personalisation.  

 Coffee Bean Logo.pngBean
(Q1 2015)

 

Behaviour Enhanced Association Network (Graph Theory)

Created new ways of representing words/strings. Made it easier to configure and troubleshoot engine. Improved reliability of learning capabilities. Reduced algorithm training time by 90%.
GOLEM.png

Golem
(Q3 2016)

  

Generalized Organisation by Layered Expanding Maps
(Neural Networks)

Creates an alternative representation of the product catalogue structure - analogous to the structure of a well merchandised physical store. Increased conversion rate by 8% compared to Bean.
   Language model  
Language_model.png

Language Model
(Q1 2015)

 Natural Language Processing (NLP)

Gives more efficient data structure and allows us to develop NLP techniques in a more flexible and scalable way. Greatly improved spelling corrections, compounded words, etc.

See it in action!

Send us your product feed in XML, JSON or CSV and we'll give you a custom demo.
 
Jorgen-Svenssons-i-Lammhult.jpg
“We chose Loop54 because the search itself was amazing! Being able to see a demo of how the search performs and learns with our products and data was key. I can’t imagine anyone choosing any other solution after seeing that! Finally, the team really care about what they're doing and really care about us being successful - not just selling their solution.”
Jörgen Bitzekis, Business Development Director at Svenssons i Lammhult
Catarina Tagebjer, E-commerce manager på Svenskt Tenn.jpg
“Just one month after implementing Loop54 we were please to see engagement with search results jump to 80%. Not only that, our engine learned 500 new search terms and attached 14500 click, add-to-cart and purchase events to both search queries and unique users - giving us tremendous insight into customer behaviour we never had before.”
Catarina Tagebjer, E-commerce Manager at Svenskt Tenn

Here are a few customers that started with a demo too

16%
Increased online revenues
70%
Reduced search exits
12%
Increased online revenues