Skip to main content
SpringerLink
Log in

Data-Driven User Complaint Prediction for Mobile Access Networks

  • Research paper
  • Published:
Journal of Communications and Information Networks

Abstract

In this paper, we present a user-complaint prediction system for mobile access networks based on network monitoring data. By applying machine-learning models, the proposed system can relate user complaints to network performance indicators, alarm reports in a data-driven fashion, and predict the complaint events in a fine-grained spatial area within a specific time window. The proposed system harnesses several special designs to deal with the specialty in complaint prediction; complaint bursts are extracted using linear filtering and threshold detection to reduce the noisy fluctuation in raw complaint events. A fuzzy gridding method is also proposed to resolve the inaccuracy in verbally described complaint locations. Furthermore, we combine up-sampling with down-sampling to combat the severe skewness towards negative samples. The proposed system is evaluated using a real dataset collected from a major Chinese mobile operator, in which, events due to complaint bursts account approximately for only 0.3% of all recorded events. Results show that our system can detect 30% of complaint bursts 3 h ahead with more than 80% precision. This will achieve a corresponding proportion of quality of experience improvement if all predicted complaint events can be handled in advance through proper network maintenance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. N. Feamster, D. G. Andersen, H. Balakrishnan, et al. Measuring the effects of internet path faults on reactive routing [J]. ACM SIGMETRICS Performance Evaluation Review, 2003, 31(1): 126–137.

    Article  Google Scholar 

  2. L. Ma, T. He, A. Swami, et al. Node failure localization via network tomography [C]//ACM SIGCOMM Conference on Internet Measurement Conference, Vancouver, 2014: 195–208.

    Google Scholar 

  3. X. Cheng, L. Fang, L. Yang, et al. Mobile big data: The fuel for datadriven wireless [J]. IEEE Internet of Things Journal, 2017, 4(5): 1489–1516.

    Article  Google Scholar 

  4. D. R. Choffnes, F. E. Bustamante, Z. Ge. Crowdsourcing service-level network event detection [C]//ACM SIGCOMM, New Delhi, 2010.

    Google Scholar 

  5. A. Gerber, J. Pang, O. Spatscheck, et al. Speed testing without speed tests: estimating achievable download speed from passive measurements [C]//ACM SIGCOMM conference on Internet measurement, Melbourne, 2010: 424–430.

    Google Scholar 

  6. H. Yan, A. Flavel, Z. Ge, et al. Argus: End-to-end service anomaly detection and localization from an isp’s point of view [C]//IEEE INFOCOM’ 12, Orlando, 2012: 2756–2760.

    Google Scholar 

  7. X. Cheng, L. Fang, X. Hong, et al. Exploiting mobile big data: sources, features, and applications [J]. IEEE Network Magazine, 2017, 31(1): 72–79.

    Article  Google Scholar 

  8. P. V. Klaine, M. A. Imran, O. Onireti, et al. A survey of machine learning techniques applied to self organizing cellular networks [J]. IEEE Communications Surveys and Tutorials, 2017, 19(4): 2392–2431.

    Article  Google Scholar 

  9. J. Friedman, T. Hastie, R. Tibshirani. The elements of statistical learning [M]. Springer, Berlin, 2009.

    MATH  Google Scholar 

  10. L. Xiao, Y. Li, G. Han, et al. A secure mobile crowd sensing game with deep reinforcement learning [J]. IEEE Transactions on Information Forensics and Security, 2018, 13(1): 35–47.

    Article  MathSciNet  Google Scholar 

  11. J. B. Caberera, B. Ravichandran, R. K. Mehra. Statistical traffic modeling for network intrusion detection [C]//8th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, San Francisco, 2000: 466–473.

    Google Scholar 

  12. Z. Zhang, J. Li, C. Manikopoulos, et al. Hide: A hierarchical network intrusion detection system using statistical preprocessing and neural network classification [C]//IEEE Workshop on Information Assurance and Security, West Point, 2001: 85–90.

    Google Scholar 

  13. C. Manikopoulos, S. Papavassiliou. Network intrusion and fault detection: A statistical anomaly approach [J]. IEEE Communications Magazine, 2002, 40(10): 76–82.

    Article  Google Scholar 

  14. B. Nguyen, Z. Ge, J. Van der Merwe, et al. Absence: Usage-based failure detection in mobile networks [C]//21st Annual International Conference on Mobile Computing and Networking, Paris, 2015: 464–476.

    Google Scholar 

  15. S. Sun, X. Wei, L. Wang, et al. Association analysis and prediction for IPTV service data and user’s QoE [C]//International Conference on Wireless Communications & Signal Processing, Nanjing, 2015: 1–5.

    Google Scholar 

  16. J. Davis, M. Goadrich. The relationship between precision-recall and ROC curves [C]//23rd International Conference on Machine Learning, Pittsburgh, PA, 2006: 233–240.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China

    Huimin Pan, Sheng Zhou & Zhisheng Niu

  2. College of Communication Engineering, Chongqing University, Chongqing, 400044, China

    Yunjian Jia

  3. Hitachi (China) Research & Development Cooperation, Beijing, 100190, China

    Meng Zheng & Lu Geng

Authors
  1. Huimin Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sheng Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yunjian Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhisheng Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Meng Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lu Geng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yunjian Jia.

Additional information

This work was sponsored in part by the National Natural Science Foundation of China (Nos. 91638204, 61571265, 61621091), and Hitachi Ltd. The associate editor coordinating the review of this paper and approving it for publication was X. Cheng.

Huimin Pan received his B.S. degree in Physics and his M.S. degree in electronic engineering from Tsinghua University, China, in 2013 and 2017, respectively. He is currently a researcher at the Cinda Jinyu (Shanghai) Investment Management Co., Ltd., and his research interests include machine learning, IoT, and big data analysis.

Sheng Zhou received his B.E. and Ph.D. degrees in electronic engineering from Tsinghua University, Beijing, China, in 2005 and 2011, respectively. From January to June 2010, he was a visiting student at the Wireless System Laboratory, Department of Electrical Engineering, Stanford University, Stanford, CA, USA. From November 2014 to January 2015, he was a visiting researcher in the Central Research Lab of Hitachi Ltd., Japan. He is currently an associate professor in the Department of Electronic Engineering, Tsinghua University. His research interests include cross-layer design for multiple antenna systems, mobile edge computing, and green wireless communications.

Yunjian Jia [corresponding author] received his B.S. degree from Nankai University, China, and his M.E. and Ph.D. degrees in Engineering from Osaka University, Japan, in 1999, 2003, and 2006, respectively. From 2006 to 2012, he was a researcher with the Central Research Laboratory, Hitachi, Ltd., where he engaged in research and development on wireless networks, and contributed to LTE and LTE-Advanced standardization in 3GPP. He is now a professor at the College of Communication Engineering, Chongqing University, Chongqing, China. He is the author of more than 80 published papers, and the inventor of more than 30 granted patents. His research interests include future radio access technologies, mobile networks, and IoT

Dr. Jia has won several prizes from industry and academia including the IEEE Vehicular Technology Society Young Researcher Encouragement Award, the IEICE Paper Award, the APCC2017 Best Paper Award, the China Industry-University-Research Institute Collaboration Innovation Award, the Yokosuka Research Park R&D Committee YRP Award, and the Top 50 Young Inventors of Hitachi. Moreover, he was a research fellowship award recipient of both International Communication Foundation and the Telecommunications Advancement Foundation Japan.

Zhisheng Niu graduated from Northern Jiaotong University (currently Beijing Jiaotong University), China, in 1985, and received his M.E. and D.E. degrees from Toyohashi University of Technology, Japan, in 1989 and 1992, respectively. During 1992-1994, he worked for Fujitsu Laboratories Ltd., Japan, and in 1994 joined with Tsinghua University, Beijing, China, where he is now a professor in the Department of Electronic Engineering. He was a visiting Researcher at the National Institute of Information and Communication Technologies (NICT), Japan (10/1995-02/1996), Hitachi Central Research Laboratory, Japan (02/1997-02/1998), Saga University, Japan (01/2001-02/2001), Polytechnic University of New York, USA (01/2002-02/2002), University of Hamburg, Germany (09/2014-10/2014), and University of Southern California, USA (11/2014-12/2014). His major research interests include queueing theory, traffic engineering, mobile Internet, radio resource management of wireless networks, and green communication and networks.

Dr. Niu has served as the Chair of Emerging Technologies Committee (2014-2015), Director for Conference Publications (2010-2011), and Director for Asia-Pacific Board (2008-2009) of IEEE Communication Society, Councilor of IEICE-Japan (2009-2011), and a member of the IEEE Teaching Award Committee (2014-2015) and IEICE Communication Society Fellow Evaluation Committee (2013-2014). He has also served as associate editorin- chief of IEEE/CIC joint publication China Communications (2012-2016), and editor of IEEE Wireless Communication (2009-2013), editor of Wireless Networks (2005-2009). He is currently serving as an area editor of IEEE Trans. Green Commun. & Networks, and is a Director for Online Content of IEEE ComSoc (2018-2019).

Dr. Niu has published 100+ journal and 200+ conference papers in IEEE and IEICE publications and co-received the Best Paper Awards from the 13th, 15th and 19th Asia-Pacific Conference on Communication (APCC) in 2007, 2009, and 2013, respectively, International Conference on Wireless Communications and Signal Processing (WCSP13), and the Best Student Paper Award from the 25th International Teletraffic Congress (ITC25). He received the Outstanding Young Researcher Award from the Natural Science Foundation of China in 2009 and the Best Paper Award from the IEEE Communication Society Asia-Pacific Board in 2013. He was also selected as a distinguished lecturer of the IEEE Communication Society (2012-2015) as well as IEEE Vehicular Technologies Society (2014-2016). He is a fellow of both IEEE and IEICE.

Meng Zheng received his B.S. and M.Sc. degrees in information sciences from Beijing Institute of Technology in 2008 and 2010, respectively. He is currently a senior researcher at the Hitachi (China) Research & Development Corporation, Beijing. He worked as a 3GPP standards expert from 2011 to 2014. His research interests include wireless networking architecture for 5G, and big data analysis in the telecommunication industry.

Lu Geng received her B.S. and M.Sc. degrees from the Beijing University of Posts and Telecommunications, in 2002 and 2005, respectively. She is currently a chief researcher at the Hitachi (China) Research & Development Corporation, Beijing. She worked as a 3GPP standards expert from 2009 to 2014. Her research interests include wireless networking technologies, IoT, and big data analysis in the telecommunication industry.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pan, H., Zhou, S., Jia, Y. et al. Data-Driven User Complaint Prediction for Mobile Access Networks. J. Commun. Inf. Netw. 3, 9–19 (2018). https://doi.org/10.1007/s41650-018-0025-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41650-018-0025-2

Keywords

Search

Navigation