Increase revenue by improving product forecasts with Machine Learning
How a high performance sports apparel retailer leveraged tailored Machine Learning models to improve their demand forecasting


The client

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.


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.

As the result of a workshop, 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™, 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.


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.

Better clustering of styles and colors was needed to identify similar products.

Forecasting brand new products based on historical performance of products with similar features.

Determining if a new product being forecasted has similar design characteristics of products that have traditionally not performed well.

The ability to guide the buy quantities for future seasons based on historical purchases, and also including the factors noted above.


The variety of features that were influencing demand meant that data related to all of these features needed to be collected and centralized before Machine Learning based, advanced analytics could be run to provide forecasting insights.

The decision was made to use Google Cloud Platform to collect all related data based on the simplicity of getting started with the cloud platform and the power of its components (storage, data processing and analytics).

The client also chose to leverage Machine Learning and Artificial Intelligence to produce high accuracy forecasts for target products, and compare these to the current forecasts.


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.

“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.”

- CEO, High End Sports Apparel Retailer

The customer initiated the commitment for a 3 year-long transformation. The goal was to continue to drive 40%+ growth in revenue, while maintaining profitability through operational excellence and maintaining the right levels of supply to meet their demand. The client also hoped to improve price setting capabilities to align better with market conditions and customer-perceived-value of their product offering.

Their goal was to achieve all of this while maintaining the core values of how they build their products and engage with the their partners for meaningful Go-to-Market and Routes-to-Market relationships. With the variety of high end sports apparel products, there were numerous factors (color, weather, sentiment and others) impacting the ability to forecast demand, making it almost impossible to generate a useful forecast. This was a classic demand forecasting problem that a Machine Learning based solution could solve.

What does it take to achieve a high accuracy product demand forecast?

The product demand forecast needs to have sufficiently high accuracy in order to drive optimized downstream supply chain planning and execution. To achieve a highly accurate forecast, multiple sets of data must be used. Internal data such as regional aspects, sales orders, order shipments, product catalog, weather information, customer sentiment, inventory levels and more needs to be analyzed for trends and correlations. Achieving this requires the ability to pull all the data together and process it at business real-time processing speeds, while leveraging advanced predictive capabilities like those provided by Artificial Intelligence and Machine Learning. The key element here is that each product and customer has unique demand patterns which can be identified and monitored efficiently through ML-based forecasting models that learn continuously. This is a perfect problem for Google Cloud Platform- with its data storage, analytics at scale and associated Machine Learning- to solve.

“Since none of our existing automated forecasting techniques were working for the products in question we had to look at Machine Learning and Artificial Intelligence as a potential solution for automated demand forecasts that our demand planners could trust.”

- Director of Demand Planning, High End Sports Apparel Retailer

Now able to get high accuracy product demand forecasts

With these objectives in mind, this high end sports apparel retailer partnered with Pluto7, leveraging Google Cloud Platform to transform their data. Utilizing analytics, Machine Learning and Artificial Intelligence, 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.

“Google Cloud Platform’s immense processing power and its state of the art machine learning capabilities led to a very high accurate demand forecast that could be delivered to the customer. It is a new paradigm in demand forecasting where you can build ML models with high level of granularity of your customer-product segmentation demand economically and plan a more realistic supply need. Customers going through this paradigm shift early on gain an advantage over others”

- Manju Devadas, CEO & Founder, Pluto7

Stronger through innovation

Working with Pluto7, this customer is experimenting with Google’s Machine Learning technology to leverage more data, analytics and Artificial intelligence. Ultimately, the objective is to achieve breakthrough innovation and business transformation by expanding the success of leveraging Google Cloud, AI and ML to related use cases and beyond.

Why Google

This client chose Google Cloud Platform because it:

  • Offers a flexible, scalable, ready-made infrastructure in the cloud.
  • Provides a cost-effective platform that’s easy for Sales team members to use.
  • Delivers speed, security, reliability and flexible pricing.

Products used

Google Cloud Platform

Google BigQuery

Google Cloud Storage

Google Cloud Dataprep

Google Machine Learning