ABSTRACT
Traditional DSL troubleshooting solutions are reactive, relying mainly on customers to report problems, and tend to be labor-intensive, time consuming, prone to incorrect resolutions and overall can contribute to increased customer dissatisfaction. In this paper, we propose a proactive approach to facilitate troubleshooting customer edge problems and reducing customer tickets. Our system consists of: i) a ticket predictor which predicts future customer tickets; and ii) a trouble locator which helps technicians accelerate the troubleshooting process during field dispatches. Both components infer future tickets and trouble locations based on existing sparse line measurements, and the inference models are constructed automatically using supervised machine learning techniques. We propose several novel techniques to address the operational constraints in DSL networks and to enhance the accuracy of NEVERMIND. Extensive evaluations using an entire year worth of customer tickets and measurement data from a large network show that our method can predict thousands of future customer tickets per week with high accuracy and signifcantly reduce the time and effort for diagnosing these tickets. This is benefcial as it has the effect of both reducing the number of customer care calls and improving customer satisfaction.
- Gteko, inc. http://www.gteko.com.Google Scholar
- Open view, hp technologies inc. http://www.openview.hp.com.Google Scholar
- B. Aggarwal, R. Bhagwan, T. Das, S. Eswaran, V. N. Padmanabhan, and G. M. Voelker. Netprints: diagnosing home network misconfgurations using shared knowledge. In NSDI'09, 2009. Google ScholarDigital Library
- P. Bahl, R. Chandra, A. Greenberg, S. Kandula, D. A. Maltz, and M. Zhang. Towards highly reliable enterprise network services via inference of multi-level dependencies. In SIGCOMM'07, 2007. Google ScholarDigital Library
- M. Y. Chen, E. Kiciman, E. Fratkin, A. Fox, O. Fox, and E. Brewer. Pinpoint: Problem determination in large, dynamic internet services. In ICDSN'02, 2002. Google ScholarDigital Library
- I. Cohen, M. Goldszmidt, T. Kelly, J. Symons, and J. S. Chase. Correlating instrumentation data to system states: a building block for automated diagnosis and control. In OSDI'04, 2004. Google ScholarDigital Library
- Y. Jin, N. Duffeld, J. Erman, P. Haffner, S. Sen, and Z.-L. Zhang. A modular machine learning system for fow-level traffc classifcation in large networks. Technical report, AT&T research, 2009.Google Scholar
- Y. Jin, N. Duffeld, A. Gerber, P. Haffner, S. Sen, and Z.-L. Zhang. Proactively detecting and troubleshooting customer dsl problems. Technical report, AT&T research, 2009.Google Scholar
- S. Kandula, D. Katabi, and J.-P. Vasseur. Shrink: a tool for failure diagnosis in ip networks. In MineNet'05, 2005. Google ScholarDigital Library
- S. Kandula, R. Mahajan, P. Verkaik, S. Agarwal, J. Padhye, and P. Bahl. Detailed diagnosis in enterprise networks. In SIGCOMM'09, 2009. Google ScholarDigital Library
- G. Khanna, M. Cheng, P. Varadharajan, S. Bagchi, M. Correia, and P. Verissimo. Automated rule-based diagnosis through a distributed monitor system. IEEE Trans. Dependable Secur. Comput., 2007. Google ScholarDigital Library
- R. R. Kompella, J. Yates, A. Greenberg, and A. C. Snoeren. Ip fault localization via risk modeling. In NSDI'05, 2005. Google ScholarDigital Library
- A. Mahimkar, Z. Ge, A. Shaikh, J. Wang, J. Yates, Y. Zhang, and Q. Zhao. Towards automated performance diagnosis in a large iptv network. In SIGCOMM'09, pages 231--242, 2009. Google ScholarDigital Library
- Y. Mao. Automated computer system diagnosis by machine learning approaches. Technical report, UPenn CIS Dept., 2005.Google Scholar
- Y. Mao, H. Jamjoom, S. Tao, and J. Smith. Networkmd: topology inference and failure diagnosis in the last mile. In IMC '07, 2007. Google ScholarDigital Library
- R. E. Schapire and Y. Singer. Boostexter: A boosting-based system for text categorization. Mach. Learn., 2000. Google ScholarDigital Library
- Y.-Y. Su, M. Attariyan, and J. Flinn. Autobash: improving confguration management with operating system causality analysis. In SOSP'07, 2007. Google ScholarDigital Library
- H. J. Wang, J. C. Platt, Y. Chen, R. Zhang, and Y.-M. Wang. Automatic misconfguration troubleshooting with peerpressure. In OSDI'04, 2004. Google ScholarDigital Library
- Y.-M. Wang, C. Verbowski, J. Dunagan, Y. Chen, H. J. Wang, C. Yuan, and Z. Zhang. Strider: A black-box, state-based approach to change and confguration management and support. In LISA'03, 2003. Google ScholarDigital Library
- C. Yuan, N. Lao, J.-R. Wen, J. Li, Z. Zhang, Y.-M. Wang, and W.-Y. Ma. Automated known problem diagnosis with event traces. In EuroSys'06, 2006. Google ScholarDigital Library
- A. X. Zheng, J. Lloyd, and E. Brewer. Failure diagnosis using decision trees. In ICAC'04, 2004. Google ScholarDigital Library
Index Terms
- NEVERMIND, the problem is already fixed: proactively detecting and troubleshooting customer DSL problems
Recommendations
Live shopping promotions: which categories should a retailer discount to shoppers already in the store?
AbstractDigitalization allows retailers to target customers with personalized promotions when they enter the store. Although traditional promotional retailer objectives, such as store visit, become obsolete once the shopper is already in the store, ...
Online coupon consumption problem
ESCAPE'07: Proceedings of the First international conference on Combinatorics, Algorithms, Probabilistic and Experimental MethodologiesNowadays, it is popular that the dealer makes profits by selling a kind of discount coupons, which can be used as money to purchase commodities with total cost less than or equal to the face value of the coupon. We can purchase a coupon at a price of 0 <...
Fixed vs. Flexible Pricing in a Competitive Market
We study the selection and dynamics of two popular pricing policies-fixed price and flexible price-in competitive markets. Our paper extends previous work in marketing, for example, Desai and Purohit 2004 by focusing on decentralized markets with a ...
Comments