Using Data to Enable Supply Chain Efficiency
American Fortune 100 corporation that designs, develops, engineers, manufactures, markets, and sells machinery, engines, financial products, and insurance to customers via a worldwide dealer network.
The leaders of this Fortune 100 company are responsible for providing large machinery and equipment to their customers but were challenged with lack of visibility, access and alternative machine parts options across the network of their supply chain. When a piece of equipment broke, it was taking a long time to replace them because there was a disconnect between the dealers and insight into available inventory.
A web based platform was designed with the ability to search machine parts across the inventory within a certain mile of radius. The search yielded results that included the machine part and alternate parts with their availability. This search functionality enabled dealers instant connection to the inventory and increased their overall speed and efficiency.
Additionally all searches are recorded to build the machine learning model. Machine learning algorithms like K-Means clustering, Hierarchical clustering, Multiple logistic regression are being used to recommend dealers on machine parts – what, when and how much to stock.
The solution is hosted on the AWS cloud platform and is built to extract data from multiple sources such as Teradata, DB2, Neo4J and Oracle. All the data is ingested into the data lake. Restful API’s are developed for data egress from the data lake.
Our team was able to deliver a number of results, including:
- Inventory Optimization and accessible dealers network
- Projected increase in sales of 15%
- Reduction of 25% on late delivery and shipping