@article{587,
  author = {Mohamed El Ghourabi, Amira Dridi, Fedya Telmoudi},
  title = {Data Mining versus Statistical Tools for Value at Risk Estimation},
  journal = {Journal of Information Technology Review},
  year = {2011},
  volume = {2},
  number = {4},
  doi = {},
  url = {http://www.dline.info/jitr/fulltext/v2n4/2.pdf},
  abstract = {Financial crises are perceived as shocking events, several researchers concentrated on the identification of stressed and stable periods in order to take strategic decisions on time. In this paper, for one hand we propose a new hybrid approach to deal with the prediction of the Value at Risk (VaR). Based on financial variables from bank’s balance sheets as input data , this approach integrate Rough Set Theory (RST), Gaussian Case Based Reasoning- clustering (GCBR-Clustering), Real valued Genetic Algorithm (RGA) with Support Vector Machines (SVM) in order to classify stressed and non stressed periods and therefore determine the VaR . The RST-GCBR Clustering-RGA-SVM combination is justified by a high accuracy rate which reaches 96.551% in cluster 1and 100% in cluster 2. In another hand we attempt to highlight the usefulness of our proposed model versus the existing one based on the extreme value theory. Based on a Kupiec backtest it is proved that our proposed approach is more performant at different confidence level.},
}