IT Quoter Product Categorisation


iSell is an Australian company which operates a web-based software service called IT Quoter. IT Quoter contains a catalogue of over 5,000,000 products, which allows companies to easily build and receive quotes on large quantities of IT products and software solutions.

project SUMMARY

UVLens is the number 1 rated sun safety app on Android and iOS. UVLens shows the danger level of ultraviolet (UV) rays throughout the day and provides personalised recommendations based on the user’s skin type.

- 500k+ worldwide users
- Featured by Apple App Store
- Editors Choice on Google Play Store‍

IT Quoter has a catalogue of more than 5,000,000 products, with additional products regularly added in the fast-paced world of tech. In order to add new products to their system they must first be tagged and categorised using information provided by the manufacturer. Unfortunately, this information is often incorrect or of poor quality, and as such requires long amounts of human-hours to manually categorise these products, regularly taking up to 30 minutes per product. In an attempt to speed this up and reduce man-hours and cost, a machine learning model was desired to automatically utilise data from the manufacturer and categorize the products accurately whilst minimising human input.

The Solution

A machine learning model was trained on over a million previously labelled products to classify the products by category based on features such as the name and description. This resulted in a model that could be integrated into a data processing pipeline and deployed at scale to automatically classify new products.

The Outcome

- The resulting model is able to categorise millions of new products within minutes, saving hours of manual time and thus costs. Previously, a single product could take up to 30 minutes to classify. 

- In addition to saving man-hours, the utilisation of machine learning has also reduced the time spent hiring and training new staff, which could take up to 8 weeks.

- The model can continuously learn and improve with new products fed through the model


project Details





View live project
Want to stay in the loop? Subscribe to get updates from us.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.