Retail Category Mapper: Difference between revisions

From Computer Laboratory Group Design Projects
Jump to navigationJump to search
(Created page with "Ecommerce retailers face a seemingly insurmountable barrier to being able to fully automate their online marketing activity. Many marketing channels, such as price comparison ...")
 
No edit summary
Line 1: Line 1:
Ecommerce retailers face a seemingly insurmountable barrier to being able to fully automate their online marketing activity. Many marketing channels, such as price comparison sites Google Shopping and Kelkoo, or marketplaces eBay and Amazon, require formatted product data, but each has its own format. Most retailers struggle to adapt their product data to these many distinct formats. This problem manifests itself mostly in the process of product category mapping: that is, the mapping of a retailer's list of product categories onto a different category taxonomy. This is an issue that has caused problems for some of the world's largest ecommerce companies, despite the fact classification has been the subject of machine learning research for decades. The aim of this project will be to develop an ecommerce-optimised machine learning tool that takes an unmapped category (and potentially other product information) and outputs a mapping and a confidence level. A user interface will need to be created to allow human users to view a list of mappings by confidence level, make manual corrections to mappings, add to the training set, and view the progress of the mapping. As an example, this [[bicycle retailer example]] should be mapped to categories in http://www.google.com/basepages/producttype/taxonomy.en-GB.txt
Ecommerce retailers face a seemingly insurmountable barrier to being able to fully automate their online marketing activity. Many marketing channels, such as price comparison sites Google Shopping and Kelkoo, or marketplaces eBay and Amazon, require formatted product data, but each has its own format. Most retailers struggle to adapt their product data to these many distinct formats. This problem manifests itself mostly in the process of product category mapping: that is, the mapping of a retailer's list of product categories onto a different category taxonomy. This is an issue that has caused problems for some of the world's largest ecommerce companies, despite the fact classification has been the subject of machine learning research for decades. The aim of this project will be to develop an ecommerce-optimised machine learning tool that takes an unmapped category (and potentially other product information) and outputs a mapping and a confidence level. A user interface will need to be created to allow human users to view a list of mappings by confidence level, make manual corrections to mappings, add to the training set, and view the progress of the mapping.  
 
As an example, this [[bicycle retailer example]]  
https://wiki.cam.ac.uk/cl-design-projects/Bicycle_retailer_example
should be mapped to categories in http://www.google.com/basepages/producttype/taxonomy.en-GB.txt

Revision as of 14:54, 30 September 2014

Ecommerce retailers face a seemingly insurmountable barrier to being able to fully automate their online marketing activity. Many marketing channels, such as price comparison sites Google Shopping and Kelkoo, or marketplaces eBay and Amazon, require formatted product data, but each has its own format. Most retailers struggle to adapt their product data to these many distinct formats. This problem manifests itself mostly in the process of product category mapping: that is, the mapping of a retailer's list of product categories onto a different category taxonomy. This is an issue that has caused problems for some of the world's largest ecommerce companies, despite the fact classification has been the subject of machine learning research for decades. The aim of this project will be to develop an ecommerce-optimised machine learning tool that takes an unmapped category (and potentially other product information) and outputs a mapping and a confidence level. A user interface will need to be created to allow human users to view a list of mappings by confidence level, make manual corrections to mappings, add to the training set, and view the progress of the mapping.

As an example, this bicycle retailer example https://wiki.cam.ac.uk/cl-design-projects/Bicycle_retailer_example should be mapped to categories in http://www.google.com/basepages/producttype/taxonomy.en-GB.txt