To significantly reduce the inventory levels of purchased parts for complex industrial product manufacturing, a leading North American discrete manufacturer implemented C3 Inventory Optimization on AWS.
The manufacturing company operates hundreds of factories globally and makes highly complex industrial equipment. Since the manufacturer carries over $4B in inventory, the ability to reduce inventory at scale drives significant financial benefit for the company.
Prior to engaging with C3, the manufacturer had experimented with various inventory optimization software offerings. However, existing software solutions were unable to dynamically optimize inventory levels of individual parts at scale while managing uncertainty and learning continually from data. Through implementing C3 Inventory Optimization, the manufacturer reduced by inventory levels by as much as 35%.
Accurately Predicting Variability
The company’s products are configured with hundreds of individual options, leading to products that have thousands of permutations. This drives significant complexity in managing inventory levels during manufacturing. To negotiate this complexity, factories often hold excess inventory to fulfill their orders on time.
In order to manage these uncertainties, company analysts maintained excess inventory, driven primarily by experience and a lack of tools to help them make informed decisions. Key sources of uncertainty include variability in demand, supplier delivery times, quality issues with items delivered by suppliers, and production line disruptions.
To reduce inventory costs and improve analyst performance, the customer selected C3 and the C3 Inventory Optimization application, given uncertainty in demand and supply. The company trialed the application on one product line at one factory, with plans to scale the solution for other product lines and factories.
Over the course of the trial, the C3 team accomplished the following:
- Received, loaded, and processed data for production orders, product configurations, bill of materials, part movement events, historical settings of reorder parameters, and lead time and shipping costs from suppliers
- Created a unified object model to represent all the inventory data, using 15 C3 Types
- Recreated historical inventory levels of individual parts by processing the various movement of parts from the point of arrival from suppliers to the factory production line
- Developed a machine learning / AI algorithm to compute part-level demand forecasts based on production orders and assemblies, and by traversing multi-level, time-varying BOM files
- Developed a stochastic optimization algorithm to dynamically optimize inventory levels
- Configured the application user interface to provide actionable insights to reduce inventory holding costs