Who is the Client

A US-based retailer with more than 700 departmental stores and 150 specialty stores, client is a major player in their industry and one of the oldest shopping destinations for their customers.

The Challenge

The client was using a rule-driven product placement (RDPP) approach on its e-commerce website to sequence products. In this approach, pre-defined rules were used to calculate a score for each product based on a formula that determined the sequence. The formula assigned weights to different behavior metrics, including previous sales, product price, inventory on hand, etc. The e-commerce experts had to assign the weights to these metrics based on their experience.

In this state, the whole process was dependent on human judgment. The entire process was stagnant and irrelevant because of changing customer behavior. The client wanted an intelligent and dynamic method based on data rather than human judgment to assign weights to different metrics dynamically and avoid human error.

The Solution

GSPANN’s Advanced Analytics team developed and deployed algorithms based on Zeolite (our in-house ML-based solution) for dynamic product sequencing. We developed two models based on the supervised ML regression model. These models predict the next day’s ‘product views’ and ‘sales dollars’ for each product by using the historical data. To rank the products, we used the predicted views as qualifiers.

Our implemented Zeolite models uses the attributes based on consumer buying patterns. As the trends change over time, the new patterns present in the recent data get accommodated in the auto-refreshed model. The current model’s refresh frequency is seven days, that auto determines weights based on the historical data. We also enabled an adhoc model re-training for special cases like different seasons, holidays or sales, etc.

The ML model has learned from 1.5+ million transaction data. We’ve A/B tested the performance of both rule-based and new ML-based models. Our ML algorithms were applied to 53 of product categories to search and browse products.

Business Impact

  • Out of 53 product categories, 42 of them saw improved revenue per session, add to basket, conversion rate, etc., which translates to a 79% success ratio.
  • In search, 100% of product categories benefited using ML algorithms, while in browsing, 78% of product categories benefited using the Zeolite-based ML algorithms.
  • Some of the most prominent product categories that benefited from the model were Women’s Watches (Michael Kors), Baby Girls and Boys, Dresses, Suits and Tuxedos, and Men’s Shoes.
  • Bags category in the women section recorded a 400% increase in sales as compared to the older methods.
  • Increase in average conversion metrics:
    • Revenue per Session – 38%
    • Order Conversion – 42%
    • Add to Bag Conversion – 20%
    • Checkout Conversion – 28%

Technologies Used

Zeolite. An AIOps framework that utilizes artificial intelligence and machine learning to detect potential failures automatically

Related Capabilities

Utilize Actionable Insights from Multiple Data Hubs to Gain More Customers and Boost Sales

Unlock the power of data insights buried deep within your diverse systems across the organization. We empower businesses to effectively collect, beautifully visualize, critically analyze, and intelligently interpret data to support organizational goals. Our team ensures good returns on the big data technology investment with effective use of the latest data and analytics tools.

Do you have a similar project in mind?

Enter your email address to start the conversation