Warranty Analysis Saves Time, Money and Brand Reputation

Comprehensive warranty analysis moves to the front burner for many progressive companies

by David Froning, SAS

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 percent of US company revenue.

Two percent is likely a conservative figure. Think of the financial, legal and image agony tire manufacturers went through several years ago, and then consider:

• How much could your company save if it could mine warranty details 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 percent of warranty claims that are fraudulent?

Analyzing warranty claims to help reduce revenue loss
The first step to solving the problem: text mining.

For several years text mining has been touted as the 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 category 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 text mining systems don't look for changes over time. Often, the software simply spits out a list of the top 20 warranty issues. What happens, though, when a type of freezer defect jumps from a ranking of 81 one week to 41 the next? It's still not on the top 20 list, and its sudden and dramatic jump goes unnoticed.

The second problem? Software that does monitor change has a tendency to throw out too many red flags. Most reporting systems identify which issues have worsened. However, in a stable system half of the issues will get better, and half will get worse. The real question is which issues have become significantly worse.

Text mining + analytics = results
Text mining alone can't identify suppliers providing the largest quantity of defective parts or name service companies that can't get a problem fixed right the first time. By combining text mining with other data analysis, however, 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 text mining results to identify statistically significant changes in failure rates, costs and other metrics. The system can then notify the appropriate engineer, saving months off 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.

If your warranty analysis solution can't do these things, it's time to check out SAS. Wherever competition is fierce, customers' expectations are high and government regulations are stringent, warranty claims analysis will pay for itself.