Posted on

Bluebungalow.com.au – Okkular Tag-gen solution case study

Okkular Tag-gen solution – Case Study


About Blue Bungalow

Blue Bungalow is a Brisbane based fashion retailer for everyday fashion and dreamy summer styles for real women. From workplace to weekend, or weekday basics to resort wear.

Emma Filliponi – Digital Marketing and
E-Commerce Manager at Blue Bungalow

What business problem were you trying to solve? 

One of our greatest challenges has been improving the depth of our product specific attribute data to improve product discovery and conversion. We know rich product data was the key factor in enhancing the user experience with better search results and in-depth product filters.

The process of adding the data was manual. The manual process is time consuming and resource hungry. There is also consistency issues with entering the data manually with a growing team. 

How was the problem affecting your business?

Limited attribute data on products was affecting our business in several ways:

  • Poor search results: see below examples:

1 result for search term “bell sleeves midi dress”

  • Limited product specific filters 
  • Unable to implement other user experience enhancement technologies due to limited product data. Rich product data is a minimum requirement for many of these technologies to work efficiently 
  • Impact on SEO/SEM due to surface level product specific data 

What options did you consider to solve this problem?

We were entering the data manually, but it was not consistent. We looked at technologies which could help us with dynamic filtering however these are only as effective as the depth of product data they have access to. We couldn’t find any other efficient option until we found Okkular.

What reservations did you have before choosing Okkular?

  • Industry reference for Okkular I.e. if anyone else had used Okkular
  • We wanted to automate the process as much as possible. i.e. Shopify app to import and export the data generated by Okkular without having to manually upload or import product data   
  • Accuracy of data generated by AI
  • Naming the data according to Blue Bungalow’s taxonomy 

Why did you choose Okkular?

The challenge with eCommerce fast fashion is balancing depth of product data, with the time it takes to manually input that information. The automation of Okkular’s AI has allowed us to enrich our product data, resulting in painless product discovery. The technology has made our team more effective, with less time spent on manual data entry and more time spent on growth initiatives. It takes Okkular minutes to do what a person would take days. A technology that solves pain points in both internal business processes & the consumer facing conversion journey is a rare find. I would go as far as to say not using a technology like Okkular, would give you a competitive disadvantage. 

What are some of the immediate business benefits you have noticed after implementing Okkular Tag-gen solution?

  • Time spent on manual data entry. It takes Okkular minutes to do what a person would take days
  • Immediate improvement in search results. See before after search results 

BEFORE:  1 Result for this search term before adding the Okkular generated meta tags

AFTER: 20 Results after Okkular Meta Tags were added 

  • Improved product filters (in development using Okkular tags)
  • 31% conversion rate lift for sessions using Site Search 
  • Ability use technologies that enrich the user experience as a direct result of the depth of data available as a result of Okkular

What are the long-term benefits you see automating the Tag gen process and providing visual search for your customers?

Immediate tangible benefits have been seen after 2 months. The long-term benefit we expect to see will be simplified product discovery resulting in an enhanced user experience and significant improvement in conversion from the combination of intelligent search & more comprehensive filtering. Using Okkular’s features like automating alt_tags, titles and long tail keywords will also benefit our SEO AND SEM initiatives. We are very excited to trial the Okkular visual search soon.   

If you would like to learn more about Okkular’s Tag-gen solution, contact 

Mahendra Harish:  mharish@okkular.io 

For more information regarding Blue Bunaglow, Check them out at https://bluebungalow.com.au

Posted on

Gamified Fashion Marketplace – Dresswhere.com, an Okkular Tag Gen Case Study

www.dresswhere.com

Key takeaways for using Okkular AI based Tag-gen solution

  • Over 8 weeks of full-time hours saved for tagging over 20k products. This helped in reducing cost and time significantly and go to market faster.
  • Produce over 20 product specific Tags/attributes for each apparel, which helped in making the search engine more efficient and robust
  • Over 80% accuracy on an average with AI classification and the ability to audit to make it 100% accurate 
  • Classify multiple colours which would have taken additional time and cost to add for every product manually. 

Intro to Dresswhere.com

Dresswhere is an upcoming aesthetic gamified search-engine for fashion. They don’t expect users to know what they want, so instead of asking them a very complex question (‘what are you looking for?’), they ask them a very simple question repeatedly: ‘which of these three apparels is best visually?’ Every time the user chooses an apparel or skips, they’re shown another three apparels that are slightly more specific to their tastes based on their previous choices. The effect is that, over the course of ~3 minutes, the user zooms in on an individually curated collection of apparels. Whenever they scroll down, they see their top results, and can click through to the retailer.

What was the pain point for Dresswhere to make the search engine efficient?

To create the Dresswhere search engine and predict a closer matching apparel, Dresswhere had to Tag every apparel’s image with at least 6-8 attributes/Tags. The catalogue inventory was over 20K products and requiring ongoing 3-4k products added every month. Dresswhere gets the product catalogue feed from multiple Fashion brands and the data received in the feed was inconsistent and was not enough for the search engine to work efficiently. While performing the task of tagging products manually, Dresswhere had two main issues.

  • Time taken/cost incurred to tag over 20k images and ongoing 3-4k products every month. Dresswhere estimated this would take approximately 9-10 weeks to tag over 20k products. 
  • The inconsistency and error rates

The above two issues were two key pain points to overcome for Dresswhere to successfully launch their product.

How did Okkular solve Dresswhere pain points?

Okkular.io has developed an AI based visual analysis solution which helps in automating the product tagging process. The AI tool generates tags from just the product images in under 15secs per product, increasing the speed to over 15 times faster compared with manual tagging. The tagging process also helps in reducing errors, generating consistent data and significantly reducing costs. 

As an example, Okkular Tag-gen solution can generate over 12 attributes for a dress including key attributes like neckline, style, length, print and also tags for occasions and avatars. The tags generated can be used in many ways including, titles, description, filters, product specific keywords, and meta tags.

Dresswhere provided us the product feed in a google feed format and the output of Tags were uploaded by connecting via Okkular API to Dresswhere platform

Working closely with Angas (Founder Dresswhere), we were able to develop additional key tags which were very specific to Dresswhere. We also trained and generated over 20 tags instead of 6 to 8 which was an initial requirement for Dresswhere if the task had to be performed manually.

During this project we frequently received feedback from Dresswhere to improve the classification accuracy, user interface and additional features which helped us co-create a solution which has not only helped Dresswhere but many other retailers using our solution currently.

What are the benefits for Dresswhere? 

  • Over 8 weeks of full-time hours saved. This helped in reducing cost and time significantly and go to market faster.
  • Produce over 20 Tags/attributes for each apparel, which helped in making the search engine more efficient and robust
  • 80% accuracy on an average with AI classification and the ability to audit to make it 100% accurate 
  • Classify colours from Apparel which would have taken additional time and cost to add for every product manually. 

Okkular is also working with Dresswhere to provide Okkular Visual search solution to help their users find similar looking products from multiple brands once they have identified a dress, they want using the Dresswhere search engine.  

If you would like to learn more about Okkular solutions, contact 

Mahendra Harish:  mharish@okkular.io 

For more information regarding Dresswhere, Check them out at https://www.dresswhere.com

Contact Angas Tiernan: angas@dresswhere.com