Catalog data enrichment for one of North America's largest multi-brand retailer with e-commerce presence

An automated product tagging impact study.

The big picture

52%

of total tags processed in the live site improving data quality

3M

products across categories over a period of 3 months 

69

new attributes with values across categories

Customer experience is in transition. Whether online or offline, what customers want and gravitate towards is being constantly redefined. Shoppers today are looking for convenient, friction-free experiences. Expectations for good retail experiences are being dictated by two things:

  1. The number of brands and marketplaces competing for shopper attention online
  2. Shoppers prioritizing ease of shopping, i.e, convenience and accessibility

The retailer is a 150+ year old premier omni-channel multi-brand retailer, with sales of $25 billion across offline and online presence. It has a strong omni channel presence and is a pioneer in delivering customer experiences that go beyond the traditional. 

They patterned with Vue.ai to improve their product data quality and improve their quality assurance process as a means to improve productivity and better customer engagement.


The need

Ecommerce data standardization is indispensable for optimizing business processes. Businesses depend on this product data coupled with advanced analytics, to expand their understanding of consumer behavior as well as to make qualitative decisions.This means data need to be in consistent, manageable conditions.

Inconsistent product data regularly slows down the digitization of products and the time it takes to get a product to the shopper
(in terms of weeks to months).

To build consistency into product data and automate standardization of data, the retailer needed a solution that would help tag, review, and remove discrepancies in product data

Improve product data quality, with case-specific, AI-generated, product tags.

Improve quality assurance process by reducing time to review product content.

Automate standardization of data discrepancies in product information that flow into the system via third-party data sources.

Vue.ai was the natural partner as the ML tagging tool enables retailers to structure and label product data efficiently. The tool can be used for building custom taxonomies and attribute structures based on business priorities. Both the output structured product data and the trained models can be exported to fit into any existing systems.

Implementation

One issue the customer faced was inconsistent or inaccurate product listing entered by multiple vendors or third-party sellers as a result of a lack of knowledge, duplication or oversight. The other problem was manually validating metadata tags which was prone to human errors like spelling mistakes, incorrect mapping, duplication of information and oversight. Data had to be exported to and imported from various sources, and from a wide range of sellers who often have different formats, vocabularies, and methods of documenting product information. Generic product content was also impacting sales and engagement.

Inconsistent product listing
With Vue.ai’s state-of-the-art image classification capabilities, deeper attribute-related information that describe products were also extracted. The Natural Language Processing (NLP) capabilities classifies and extract features from differing sources of metadata about the product and its attributes.

Discrepancies in information from various sellers:
Automated product tagging audits data entries to identify missing data, incomplete metadata or duplication of images across sellers. It helps reconcile visually and textually extracted attributes. This highlights inconsistencies and/or boost the confidence and accuracy of attributes that have contextual cues from the different sources.

Manual Quality Assessment (QA):

With QA, algorithms improved, improving accuracy over iterations of feedback. The algorithms also identified confidence cut-off beyond which margin of error was acceptable, reducing the need to QA

With the current tagging process & efficiency, Vue.ai was able to correct 51.82% of total tags processed in the live site—i.e., their existing product catalog, improving data quality in the process.

Case-specific product tagging:

In addition to the rich attributes extracted, attributes are mapped to specific taxonomy along with confidence values for the extracted attributes, improving the predictions made.

For this client, Vue.ai's automated product tagging solution predicted tags for over 3 Million products across categories over a period of 3 months. Over this period, it added 69 new attributes, values covering 18 attributes & 21 Product types across 3 categories.

Key takeaways

Automated Product Tagging helps in standardizing the fundamentals of a business’ operation - the product data. With better product data, you can unify product information across channels, and make informed decisions. Automated Product Tagging bears numerous benefits, mainly:

  • Product Catalog enriched with highly specific fashion tags
  • Automate/ heavily machine-assist product annotation and digitization process
  • Increased engagement as a result of improved site search
  • Easy vendor onboarding and third party data ingestion
  • Enriched metadata that enables higher SEO ranking for your products