With the rapid development of wireless communication technology, the use of mobile phones and other means of communication for telecommunications fraud has become a major problem that endangers user security. Aiming at this problem, this paper constructs a telecom fraud user detection model by in-depth analysis and mining of cellular network data. The model includes data processing, CNNcombine algorithm and model evaluation. First, in the data processing part, the data set is subjected to feature screening, coding, sampling, and the like. Secondly, the CNNcombine algorithm is a combination of a one-dimensional convolutional neural network and multiple traditional classification algorithms. The convolutional neural network is applied to solve classification problems other than text image signals. Finally, in the model evaluation part, it is proved that the CNNcombine algorithm has higher accuracy than the common machine learning classification algorithm such as XGBoost to detect telecom fraud users.
[1]
G. G. Stokes.
"J."
,
1890,
The New Yale Book of Quotations.
[2]
Yoav Freund,et al.
A decision-theoretic generalization of on-line learning and an application to boosting
,
1995,
EuroCOLT.
[3]
J. Friedman.
Greedy function approximation: A gradient boosting machine.
,
2001
.
[4]
Joseph Sill,et al.
Feature-Weighted Linear Stacking
,
2009,
ArXiv.
[5]
N. Takahashi,et al.
Analysis of signal propagation in 1-D CNNs with the antisymmetric template
,
2010,
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010).
[6]
Tianqi Chen,et al.
XGBoost: A Scalable Tree Boosting System
,
2016,
KDD.
[7]
S. Rigatti.
Random Forest.
,
2017,
Journal of insurance medicine.