bg

Transform Your Supply Chain Planning and Marketing Strategies with Google Cloud and SAP Integration

Cloud Marketplace

Explore Pi Agent pi-logo

High-performance sports apparel retailer leveraged tailored Machine Learning models to improve their demand forecasting

succes stories images

“With the success of the proof of concept we are now in a position to achieve the demand forecast accuracy for our products that will help with procurement planning and result in cost reduction as well ensure we do not lose revenue due to stockouts.”

-CEOHigh-performance sports apparel retailer

Introduction

This company designs and sells high end, high-performance sports apparel products through multiple channels. Their stated ethos is one of enabling people to better enjoy the outdoors and the wonders of nature. Continuous innovation and improvements in material science are at the heart of the company’s vision and philosophy. Today, their inspired collections reflect continuing commitment to offer high functioning apparel for all ages and outdoor activities, from back-to-school and around town, to the high mountains. This retailer is keen to embark on a digital transformation effort to scale and improve their processes.

Why We Chose Pluto7

The client is already well aware of the changing buying patterns of their customers and understands when, where, why and how their customers will buy their products. Because of this, their focus is on building strong customer loyalty through the high quality, high-performance products they have prided themselves on making for 72 years. The client looked to Pluto7 to help them leverage the power of Cloud (GCP) and Machine Learning, in the hope that they could align these efforts to their growth, industry trends, and economics of their business model.

Solution

The client and Pluto7 team decided to focus on the demand forecasting use case for their Proof of Concept. The aim was to proactively reduce excess and obsolete inventory through better demand forecasting, while also increasing revenue. The findings from the Proof of Concept would then be used to plan for their next production release.

By using Pluto7’s Demand ML solution, the company achieved a demand forecast with greater than 85%+ accuracy compared to a baseline of forecast that was not meeting their expectations. This helped the customer successfully reach their target for the Proof of Concept.

Results

Pluto7 and GCP helped them create product demand forecasts with over 85%+ accuracy, and one Machine Learning forecast that consistently beat their current forecast.  With Pluto7’s expertise in Advanced Analytics, Machine Learning, and Artificial Intelligence, the team was able to identify the right Google solutions and quickly develop a Proof of Concept that demonstrated how to use both internal and external data to produce a multi-attribute product forecast with high accuracy.

Enable Decision Intelligence Into Every Corner Of Your Product And Operations.

industry image

Industry Retail

Platform Demand-ml

Challenges

  • The client needed better forecasting to predict at the ‘color’ and ‘style’ level of each product.
  • The client needed to be able to correlate weather and regional factors when considering demand, given the nature of their products.
  • Forecasting brand new products based on historical performance of products with similar features.
  • The ability to guide the buy quantities for future seasons based on historical purchases, and also including the factors noted above.

Results

  • ML and AI models were able to develop a demand forecast with over 85%+ accuracy for the target set of products selected for the Proof of Concept.
  • With this high level of accuracy, business leads felt comfortable adopting the same for other products and planned for change management driving adoption of ML generated forecasts.
  • This was driven by the results from the parallel tests conducted, which proved that the Machine Learning model performed much better than their existing demand forecasts.

Products Used

  • Google Cloud Platform
  • Google Cloud Storage
  • Google Cloud Dataprep
  • TensorFlow
  • Google BigQuery