When was the last time warranty claim issues made it to the top of your operational to-do list? Perhaps it happened after the marketing department complained about a poor review in a consumer magazine. Or worse, when the legal department called to let you know about a lawsuit.
For too many companies, warranty claims are not a high priority unless undertaken to avoid something -- angry customers, alienated dealers or a public relations debacle. This holds true despite the fact that warranty claims eat up 2% of U.S. company revenue.
Two percent is likely a conservative figure. Think of the financial, legal and image agony tire manufacturers went through several years ago, then consider:
- How much could your company save if it could mine warranty detail quickly enough to isolate defects and stop newly defective merchandise from leaving the factory?
- How much could your company save if it decreased or eliminated the 10% of warranty claims that are fraudulent?
- Does the 2% of revenue figure include the PR and legal costs for companies that are slow to respond to a serious warranty problem?
Reducing revenue loss starts with analyzing warranty claims. But software designed to do that isn't created alike. Most companies are swimming in data -- much of it ends up being useless.
Text Mining Is The First Step To Solving The Problem
For several years text mining has been touted as a solution to warranty issues, particularly the issue of quickly identifying problem areas and fixing them. Instead of technicians trying to select from hundreds of warranty categories or clerks trying to guess which of hundreds of warranty categories a technician's written assessment belongs in, text mining software is supposed to read written assessments and devise a list of the top warranty areas.
There have been two problems with this approach. First, most programs don't look for changes over time. Often, the software simply spits out a list of the Top 20 warranty claims. What happens, though, when a type of freezer defect jumps from a ranking of 200 one week to 25 the next? It's still off the Top 10 list and more importantly its sudden and dramatic jump in occurrence goes unnoticed.
The second problem has been the software's tendency to throw out too many red flags. A simple reporting system answers this question: Which plant/model combination has the highest failure score? The more useful question would be; which plant/model combination is significantly worse?
Text Mining + Analytics = Results
Text mining alone can't help companies identify suppliers providing the largest quantity of defective parts or name service companies that can't seem to get a problem fixed right the first time. By combining text mining with other data sources, companies can quickly spot problems with different manufacturing sites or within a manufacturing plant.
When you combine text mining with analytics, a reliability engineer has so much more information to consider. For instance, analytic-based systems can use the results of text mining to automatically identify statistically significant changes in failure rates, costs and other metrics. The system can then notify the appropriate engineer of the issues, saving months off of the issue detection process.
Warranty analysis software can also flag questionable claims so fraud can be detected before the claim is paid. And it can provide executives with a simple-to-read scorecard on warranty issues updated automatically.
Appliance Manufacturer Sees 14% Reduction In Warranty Costs
The Sub-Zero Co. in Madison, Wisc. had a warranty analysis process in place that was supposed to help catch defects quickly and -- ultimately -- improve customer satisfaction. Reliability engineers say it gave them plenty of historical data, but it couldn't detect trends quickly because it relied on reading technician reports and making judgments about what the problem was, leading to widespread inconsistencies. Readers had their favorite codes and sudden spikes in problem areas were often the result of staff turnover coupled with a new person's fresh interpretation of the same problem. Once the information was uploaded, the company's reliability engineers could sort the data and create trend graphs and charts, but it was extremely time-consuming.
A text mining solution coupled with analytical software removes subjectivity from the coding process. Additionally an automated email is created when a problem emerges.
The system also allows the reliability engineers to create meaningful charts very quickly. No need to write queries, export data to Excel and fix the formatting. The enhanced ease allowed one engineer at Sub-Zero to discover that a chronic door hinge problem that was thought to be part of an overall hinge problem was actually two separate problems. Problems are now discovered quickly enough in a new model that changes are made before additional models with a defect get shipped. Issue detection, definition, and resolution times have all improved, causing warranty claims costs to decrease by 14%.
Warranty analysis is critical for success in the durable-goods marketplace. Wherever competition is fierce, customers' expectations are high and government regulations are more stringent, warranty claims activity will be increasingly important to analyze and understand.
David Froning is the warranty analysis product manager for SAS Institute. www.sas.com
© SAS Institute, 2006