Algorithm version | Context model | Description |
Topic Model |
Topic Modelling |
Determined underlying structure by clustering words that are used in the same context. Created initial ability to find Related Results. |
Batman |
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. |
Bean |
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 |
Generalized Organisation by Layered Expanding Maps |
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 |
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. |
Send us your product feed in XML, JSON or CSV and we'll give you a custom demo.