中文摘要：

在设计地方政府债务风险预警指标体系框架的基础上,吸收了粗糙集和BP神经网络等人工智能方法在数据处理上的优点,构建出基于粗糙集-BP神经网络集成的地方政府债务风险非线性仿真预警系统。选取我国2007～2009年东、中、西部地区9个县的27个样本数据,运用该非线性仿真预警系统进行了地方政府债务风险预警实证分析。研究结果表明,大部分样本地区的债务风险都处于＂中警＂及以上状态,地方政府债务风险普遍较高,同时,样本地区债务风险综合评价值是不断提高的,说明近年来我国地方政府债务风险呈现出不断上升的趋势。与单纯的BP神经网络仿真预警系统相比,该仿真预警系统不仅降低了BP神经网络的复杂性,节省了训练时间,而且具有更好的预警准确性和推广应用价值。

英文摘要：

Firstly, the paper designs the early-warning indicator system of the local government debt risk. Then, the paper inte- grates rough sets and BP neural network to build the nonlinear simulation early-warning system of the local government debt risk. Se- lecting china＇s eastern, central and western regions 27 samples to carry out the empirical research in the period 2007-2009, the re- suits show that Most of the debt risks in sample regions show the state of ＂middle warning degree＂ or above the state, the local gov- ernment debt risk is totally high. Meanwhile, in the period 2007 to 2009, the comprehensive evaluation of the risk in all sample re- gions is rising, which also illustrates the local government debt risk in our country are showing a rising trend in recent years. Regard- ing the simulation effect, compared to the system of simple BP neural network, the RS-BP neural network system not only reduces the complexity of BP neural network, saving training time, but also has better early-warning accuracy and application value.