o9 Solutions, Inc. Case Studies Revolutionizing Retail Operations with AI/ML: A Canadian Retail Leader's Journey

Edit This Case Study Record

	Revolutionizing Retail Operations with AI/ML: A Canadian Retail Leader's Journey o9 Solutions, Inc.

Revolutionizing Retail Operations with AI/ML: A Canadian Retail Leader's Journey

o9 Solutions, Inc.

Technology Category	Analytics & Modeling - Machine Learning Functional Applications - Inventory Management Systems
Applicable Industries	Automotive Retail
Applicable Functions	Logistics & Transportation Warehouse & Inventory Management
Use Cases	Demand Planning & Forecasting Inventory Management
Challenge	A leading Canadian retailer, operating across automotive, hardware, sports, and leisure sectors, was grappling with the challenge of accurately predicting consumer demand and efficiently distributing inventory across its network. The retailer's demand forecasting was hampered by the lack of ability to incorporate various external demand drivers such as weather, demographics, pricing, promotions, product assortment, and location. This was particularly problematic for fashion and seasonal merchandise. Additionally, the allocation process was highly manual and relied on backward-looking information, without considering tailored allocations to stores. The stores were also running over capacity without leveraging intelligence to assist in prioritizing the distribution of new and profitable styles. Read More
About Customer	The customer is a leading Canadian retailer with operations spanning across various sectors including automotive, hardware, sports, and leisure. The company has a vast network of 220 brick and mortar stores, as well as E-commerce channels, and manages half a million SKUs. The retailer was facing challenges in accurately predicting consumer demand and efficiently distributing inventory across its network. The manual and backward-looking allocation process, along with the lack of intelligence in managing store capacity, were further exacerbating the issues. The company sought to leverage advanced technology to enhance its demand forecasting, inventory allocation, and store capacity management processes. Read More
Solution	The retailer partnered with o9, an AI platform, to enhance its demand forecasting and inventory allocation processes. With o9, the company could bring in and model various demand constraints under one platform, driving an enhanced AI/ML-based forecast for half a million SKUs across 220 brick and mortar stores, as well as E-commerce channels. The allocation process was automated and managed by exception, resulting in significant productivity gains and freeing up time for the business to focus on strategies, analysis, and inventory policies. The process leveraged ML-based forecasts, inventory strategies, and store-specific size profiles to ensure that the right items were replenished to the stores. Additionally, the retailer could manage store capacity by having full visibility into projected capacity utilization and by applying auto-correction. This was achieved by prioritizing and flowing profitable styles to stores and mitigating inventory issues. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Functional Applications - Inventory Management Systems

Applicable Industries

Automotive

Retail

Applicable Functions

Logistics & Transportation

Warehouse & Inventory Management

Use Cases

Demand Planning & Forecasting

Inventory Management

Challenge

A leading Canadian retailer, operating across automotive, hardware, sports, and leisure sectors, was grappling with the challenge of accurately predicting consumer demand and efficiently distributing inventory across its network. The retailer's demand forecasting was hampered by the lack of ability to incorporate various external demand drivers such as weather, demographics, pricing, promotions, product assortment, and location. This was particularly problematic for fashion and seasonal merchandise. Additionally, the allocation process was highly manual and relied on backward-looking information, without considering tailored allocations to stores. The stores were also running over capacity without leveraging intelligence to assist in prioritizing the distribution of new and profitable styles.

About Customer

The customer is a leading Canadian retailer with operations spanning across various sectors including automotive, hardware, sports, and leisure. The company has a vast network of 220 brick and mortar stores, as well as E-commerce channels, and manages half a million SKUs. The retailer was facing challenges in accurately predicting consumer demand and efficiently distributing inventory across its network. The manual and backward-looking allocation process, along with the lack of intelligence in managing store capacity, were further exacerbating the issues. The company sought to leverage advanced technology to enhance its demand forecasting, inventory allocation, and store capacity management processes.

Solution

The retailer partnered with o9, an AI platform, to enhance its demand forecasting and inventory allocation processes. With o9, the company could bring in and model various demand constraints under one platform, driving an enhanced AI/ML-based forecast for half a million SKUs across 220 brick and mortar stores, as well as E-commerce channels. The allocation process was automated and managed by exception, resulting in significant productivity gains and freeing up time for the business to focus on strategies, analysis, and inventory policies. The process leveraged ML-based forecasts, inventory strategies, and store-specific size profiles to ensure that the right items were replenished to the stores. Additionally, the retailer could manage store capacity by having full visibility into projected capacity utilization and by applying auto-correction. This was achieved by prioritizing and flowing profitable styles to stores and mitigating inventory issues.

Impact #1	The implementation of the o9 platform revolutionized the retailer's operations. The AI/ML-based forecasting significantly improved the accuracy of demand prediction, enabling the retailer to better manage its inventory. The automation of the allocation process not only increased productivity but also ensured that the right items were replenished to the stores, leading to increased in-stocks. The visibility into projected capacity utilization and the application of auto-correction helped manage store capacity more effectively. The retailer could prioritize and flow profitable styles to stores, mitigating inventory issues. The solution also replaced the existing system, Blue Yonder, and was chosen for its open architecture AI platform, thought leadership, and speed to value.

Impact #1

The implementation of the o9 platform revolutionized the retailer's operations. The AI/ML-based forecasting significantly improved the accuracy of demand prediction, enabling the retailer to better manage its inventory. The automation of the allocation process not only increased productivity but also ensured that the right items were replenished to the stores, leading to increased in-stocks. The visibility into projected capacity utilization and the application of auto-correction helped manage store capacity more effectively. The retailer could prioritize and flow profitable styles to stores, mitigating inventory issues. The solution also replaced the existing system, Blue Yonder, and was chosen for its open architecture AI platform, thought leadership, and speed to value.

Benefit #1	Improved forecast accuracy
Benefit #2	Increased in-stocks
Benefit #3	Improved planner productivity

Benefit #1

Improved forecast accuracy

Benefit #2

Increased in-stocks

Benefit #3

Improved planner productivity

Download PDF Version

Overview

Revolutionizing Retail Operations with AI/ML: A Canadian Retail Leader's Journey

Operational Impact

Quantitative Benefit