Data mining, fraud detection and mobile telecommunications: call pattern analysis with unsupervised neural networks

Huge amounts of data are being collected as a result of the increased use of mobile telecommunications. Insight into information and knowledge derived from these databases can give operators a competitive edge in terms of customer care and retention, marketing and fraud detection. One of the strategies for fraud detection checks for signs of questionable changes in user behavior. Although the intentions of the mobile phone users cannot be observed, their intentions are reflected in the call data which define usage patterns. Over a period of time, an individual phone generates a large pattern of use. While call data are recorded for subscribers for billing purposes, we are making no prior assumptions about the data indicative of fraudulent call patterns, i.e. the calls made for billing purpose are unlabeled. Further analysis is thus, required to be able to isolate fraudulent usage. An unsupervised learning algorithm can analyse and cluster call patterns for each subscriber in order to facilitate the fraud detection process. This research investigates the unsupervised learning potentials of two neural networks for the profiling of calls made by users over a period of time in a mobile telecommunication network. Our study provides a comparative analysis and application of Self-Organizing Maps (SOM) and Long Short-Term Memory (LSTM) recurrent neural networks algorithms to user call data records in order to conduct a descriptive data mining on users call patterns. Our investigation shows the learning ability of both techniques to discriminate user

[1]  Klaus Boehm,et al.  Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction , 1994, Electronic Imaging.

[2]  Jürgen Schmidhuber,et al.  Unsupervised Learning in Recurrent Neural Networks , 2001 .

[3]  Mark B. Ring.  Learning Sequential Tasks by Incrementally Adding Higher Orders , 1992, NIPS.

[4]  Tom Fawcett,et al.  Adaptive Fraud Detection , 1997, Data Mining and Knowledge Discovery.

[5]  E. Jonsson,et al.  Combining fraud and intrusion detection-meeting new requirements - , 2000 .

[6]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[7]  Ray J. Frank,et al.  Applications of neural networks to telecommunications systems , 1999 .

[8]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[9]  Hiroshi Wakuya,et al.  Time series prediction with a neural network model based on bidirectional computation style: An analytical study and its estimation on acquired signal transformation , 2003 .

[10]  R. Shortland,et al.  Data mining applications in BT , 1995 .

[11]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[12]  Joos Vandewalle,et al.  A hybrid system for fraud detection in mobile communications , 1999, ESANN.

[13]  D20 - Project final report and results of trials , 1987 .

[14]  Hiroshi Wakuya,et al.  Time Series Prediction with a Neural Network Model Based on Bi-directional Computation Style: An Analytical Study and Its Estimation on Acquired Signal Transformation , 2002 .

[15]  J. C. Hardin,et al.  Introduction to time series analysis , 1986 .

[16]  Michael Collins,et al.  Telecommunications crime - Part 1 , 1999, Comput. Secur..

[17]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[18]  Eric Wan,et al.  Finite Impulse Response Neural Networks for Autoregressive Time Series Prediction , 1993 .

[19]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[20]  T. Kohonen,et al.  Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum , 2003 .

[21]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[22]  F. Gers,et al.  Long short-term memory in recurrent neural networks , 2001 .

[23]  Ronald J. Brachman,et al.  Brief Application Description; Visual Data Mining: Recognizing Telephone Calling Fraud , 2004, Data Mining and Knowledge Discovery.

[24]  Masoud Mohammadian.  Intelligent Agents for Data Mining and Information Retrieval , 2004 .

[25]  Judith E. Dayhoff,et al.  Trajectory recognition with a time-delay neural network , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[26]  Michael C. Mozer,et al.  Induction of Multiscale Temporal Structure , 1991, NIPS.

[27]  Ah Chung Tsoi,et al.  Classification of Electroencephalogram Using Artificial Neural Networks , 1993, NIPS.

[28]  Hazel Heath.  Beating the bugs: An infection seven times more common than MRSA is posing severe risks to the health of older people, says Hazel Heath , 2005 .

[29]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[30]  Aluizio F. R. Araújo,et al.  A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case , 2003, Neural Computation.

[31]  Kazuo J. Ezawa,et al.  Fraud/Uncollectible Debt Detection Using a Bayesian Network Based Learning System: A Rare Binary Outcome with Mixed Data Structures , 1995, UAI.

[32]  Terrence J. Sejnowski,et al.  Unsupervised Discrimination of Clustered Data via Optimization of Binary Information Gain , 1992, NIPS.

[33]  Jürgen Schmidhuber,et al.  LSTM can Solve Hard Long Time Lag Problems , 1996, NIPS.

[34]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[35]  Guo-Zheng Sun,et al.  Time Warping Invariant Neural Networks , 1992, NIPS.

[36]  G. Cottrell.  Optimization of Entropy with Neural Networks , 1995 .

[37]  Yoshua Bengio,et al.  Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .

[38]  John W. Sammon,et al.  A Nonlinear Mapping for Data Structure Analysis , 1969, IEEE Transactions on Computers.

[39]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[40]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[41]  Michel Verleysen,et al.  Are they really neighbors? A statistical analysis of the SOM algorithm output , 2001, AISTATS.

[42]  Ray J. Frank,et al.  The detection of fraud in mobile phone networks , 1996 .

[43]  Tom Fawcett,et al.  Combining Data Mining and Machine Learning for Effective User Profiling , 1996, KDD.

[44]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[45]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[46]  Jaakko Hollmén,et al.  User profiling and classification for fraud detection in mobile communications networks , 2000 .

[47]  R. Palmer,et al.  , Introduction to the Theory of Neural Computation 1 , 2007 .

[48]  Jouko Lampinen,et al.  Self-Organizing Maps in data analysis - notes on overfitting and overinterpretation , 2000, ESANN.

[49]  Kazuo J. Ezawa,et al.  Constructing Bayesian Networks to Predict Uncollectible Telecommunications Accounts , 1996, IEEE Expert.

[50]  Moninder Singh,et al.  Learning Goal Oriented Bayesian Networks for Telecommunications Risk Management , 1996, ICML.

[51]  Judith E. Dayhoff,et al.  Adaptive time-delay neural network for temporal correlation and prediction , 1992, Other Conferences.

[52]  Lynne Pearce.  Beating the bugs. , 2004, Nursing standard (Royal College of Nursing (Great Britain) : 1987).

[53]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[54]  Sheldon B. Kopp,et al.  The good guys , 1976, Journal of Contemporary Psychotherapy.

[55]  John Shawe-Taylor,et al.  Frameworks For Fraud Detection In Mobile Telecommunications Networks , 1996 .

[56]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[57]  John Shawe-Taylor,et al.  Novel Techniques for Fraud Detection in Mobile Telecommunication Networks , 2007 .

[58]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[59]  Christian W. Omlin,et al.  Recurrent Neural Networks for Signature Verification , 2003 .

[60]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[61]  Paul Gray,et al.  Introduction to Data Mining and Knowledge Discovery , 1998, Proceedings of the Thirty-First Hawaii International Conference on System Sciences.

[62]  David J. Hand,et al.  Statistical fraud detection: A review , 2002 .

[63]  John Shawe-Taylor,et al.  Detecting Cellular Fraud Using Adaptive Prototypes. , 1997, AAAI 1997.

[64]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[65]  Jacek M. Zurada,et al.  Bi-directional computing architecture for time series prediction , 2001, Neural Networks.

[66]  John Shawe-Taylor,et al.  BRUTUS - A Hybrid Detection Tool , 1997 .

[67]  James Hammerton,et al.  Named Entity Recognition with Long Short-Term Memory , 2003, CoNLL.

[68]  Jürgen Schmidhuber,et al.  Finding temporal structure in music: blues improvisation with LSTM recurrent networks , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[69]  Zoran Obradovic,et al.  Data mining techniques for designing neural network time series predictors , 2000 .

[70]  Alexander H. Waibel,et al.  The Tempo 2 Algorithm: Adjusting Time-Delays By Supervised Learning , 1990, NIPS.

[71]  Joos Vandewalle,et al.  Detection of Mobile Phone Fraud Using Supervised Neural Networks: A First Prototype , 1997, ICANN.

[72]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[73]  Peter Hoath.  Telecoms fraud, the gory details , 1998 .

[74]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[75]  Samuel Kaski,et al.  Bibliography of Self-Organizing Map (SOM) Papers: 1981-1997 , 1998 .