Multi-label binary sequence classification model developed by Dejan Marketing.

The model is designed to be deployed in an automated pipeline capable of classifying search query intent for thousands (or even millions) of search queries from common data sources such as Google Search Console, SEMRush, Ahrefs, Moz, Majestic and Google Ads.

This is a demo model which may occasionally misclassify some queries. In a typical commercial project, a larger model is deployed for the task, and in special cases, a domain-specific model is developed for the client.

Engage Our Team

Interested in using this in an automated pipeline for bulk query processing?

Please book an appointment to discuss your needs.

Base Model

albert/albert-base-v2

Output

A list of binary classes (0,1) for 10 classification labels.

Labels

LABEL_0: 'Commercial'
LABEL_1: 'Non-Commercial'
LABEL_2: 'Branded' # Needs-further fine-tuning.
LABEL_3: 'Non-Branded' # Needs-further fine-tuning.
LABEL_4: 'Informational'
LABEL_5: 'Navigational'
LABEL_6: 'Transactional'
LABEL_7: 'Commercial Investigation'
LABEL_8: 'Local'
LABEL_9: 'Entertainment'

Sources of Training Data

Owayo:

USA, Australia, Germany, UK, Canada