Early Warning from Car Warranty Data using a Fuzzy Logic Technique

Car manufacturers are interested to detect evolving problems in a car fleet as early as possible so they can take preventive actions and deal with the problems before they become widespread. The vast amount of warranty claims recorded by the car dealers makes the manual process of analyzing this data hardly feasible. This chapter describes a fuzzy-based methodology for automated detection of evolving maintenance problems in massive streams of car warranty data. The empirical distributions of time-to-failure and mileage-to-failure are monitored over time using the advanced, fuzzy approach to comparison of frequency distributions. The authors’ fuzzy-based early warning tool builds upon an automated interpretation of the differences between consecutive histogram plots using a cognitive model of human perception rather than “crisp” statistical models. They demonstrate the effectiveness and the efficiency of the proposed tool on warranty data that is very similar to the actual data gathered from a database within General Motors.

[1]  Abraham Kandel,et al.  Perception-Based Analysis of Engineering Experiments in the Semiconductor Industry , 2002, Int. J. Image Graph..

[2]  A. Kandel,et al.  Automated perceptions in data mining , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

[3]  Abraham Kandel,et al.  Real-time data mining of non-stationary data streams from sensor networks , 2008, Inf. Fusion.

[4]  Jerry M. Mendel,et al.  Type-2 fuzzy logic systems , 1999, IEEE Trans. Fuzzy Syst..

[5]  Jerald F. Lawless,et al.  Nonparametric estimation of a lifetime distribution when censoring times are missing , 1998 .

[6]  Abraham Kandel.  Fuzzy Comparison of Frequency Distributions , 2002 .

[7]  Kazuyuki Suzuki,et al.  Estimation of Lifetime Parameters From Incomplete Field Data , 1985 .

[8]  J. F. Lawless,et al.  Some Issues in the Collection and Analysis of Field Reliability Data , 1992 .

[9]  Abraham Kandel,et al.  The Foundations of Rule-Based Computations in Fuzzy Models , 1996 .

[10]  Jerald F. Lawless,et al.  Statistical Analysis of Product Warranty Data * , 1998 .

[11]  Lior Rokach,et al.  CHANGE DETECTION IN CLASSIFICATION MODELS INDUCED FROM TIME SERIES DATA , 2004 .

[12]  Vijayan N. Nair,et al.  Estimation of reliability in field-performance studies , 1988 .

[13]  Kazuyuki Suzuki,et al.  Statistical Analysis of Marginal Count Failure Data , 2001, Lifetime data analysis.

[14]  Yuval Shavitt,et al.  Spotting out emerging artists using geo-aware analysis of P2P query strings , 2008, KDD.

[15]  J Lawless,et al.  Methods for the estimation of failure distributions and rates from automobile warranty data , 1995, Lifetime data analysis.

[16]  William Q. Meeker,et al.  Early Detection of Reliability Problems Using Information From Warranty Databases , 2002, Technometrics.

[17]  John D. Kalbfleisch,et al.  Methods for the analysis and predic tion of warranty claims , 1991 .

[18]  Kazuyuki Suzuki.  Nonparametric Estimation of Lifetime Distributions from a Record of Failures and Follow-Ups , 1985 .