 |
Home  Case studies Manufacturing
| Using automated processes to achieve 98% accuracy in commodity classification of data from 71 plants |
| |
 |
| |
| The client |
| A Fortune 200 forest products company with diversifications into building wood products, containerboard, pulp, paper and packaging. The company has 50,000+ employees around the world and revenues in excess of $20 billion. The client's operations are spread across more than 15 countries. |
| |
| The business challenge |
The client wanted to:
 |
Lower the cost of purchased MRO goods and services |
|
Establish the foundation for information management and future process integration |
After conducting a pilot, the client decided to scale MRO supply intelligence to include 71 plants and deliver enterprise scale savings.
Consolidating data from over 15 distinct systems, in one of the largest initiatives of its kind threw up a series of unexpected challenges for the client. The common material master data refused to support threshold capability levels. Inappropriate classification schemes resulted in poor search capability and limited business-relevant information. The engagement timelines and a follow-on ERP implementation were at risk. |
| |
| The solution |
Working with subject experts, Wipro diagnosed the following shortcomings in the supply intelligence initiative.
|
The subject matter experts were overloaded, trying to resolve discrepancies and eliminate duplicates in approximately of 400,000 distinct records |
|
Business need requirements had been reviewed and an off-the-shelf classification scheme had been implemented |
|
Improper classification of some of the materials resulted in poor search capabilities |
|
Effort expenditure on low-value attributes due to lack of definition of business criticality of the attributes |
Wipro helped the client address the following critical issues by:
|
Deploying data management process models for the engagement that allowed requirements to be gathered from a ‘use’ perspective |
|
Working with business users to identify business information significant to the supply professionals. These were translated into attributes that were prioritized |
|
Leveraging domain experts to review and rationalize the taxonomy of the classification scheme, reducing the number of nodes from 3500 to 2000. The scheme was restructured to a hierarchical structure to allow users to expand search capability |
|
Using automated tools and domain experts for upfront duplicate identification based on material manufacturer and vendor information |
|
Utilizing leading-edge data classification and rationalization services to reduce the load on subject experts by automated data normalization and duplicate identification |
|
| |
| Business benefits |
| The client now has accurate, consistent information about MRO goods and services purchased across the organization and can make informed decisions about sourcing and procurement.
The automated processes have resulted in 98% accuracy in commodity classification and eliminated over 29% of duplicates. |
|
 Case Studies Home
Customer List
Customer Testimonials |
|
 |
 Subscribe to 'Peer Ping' our monthly newsletter
 Request for Information
 Contact Us
Related Links
 Helping Olympus capture the
Chinese market
Equipping Sanyo to meet fluctuating consumer demand |
