基于改进灰色神经网络的房地产价格走势分析

针对房地产价格走势状况，通过对灰色预测模型GM（1，1）和BP神经网络的研究，将两大模型进行组合改良，形成新的组合灰色神经网络预测模型，以南京市中房指数为例，以Matlab为预测工具，进行2013年12个月份的价格指数预测，研究结果证明新的组合预测模型精度较高，可为房地产价格指数的预测和研究提供参考依据。

Analysis of Real Estate Price Trend Based on Modified Gray Neural Network Model

The GM （ 1,1 ） model, test of GM （ 1,1 ） and the principle of the BP neural network prediction model were brief- ly introduced. Based on the modified GM （ 1,1 ） model and the BP neural network prediction model, a new grey BP neural net- work forecasting model was designed and built. By exploiting the data from the Nanjing housing price index of China Real Estate Index System （CREIS） , the combined model was used to forecast CREIS of Nanjing index of china real estate using MATLAB. According to the prediction results, the combined prediction model has overcome the defects of one single model to a great extent. The model improved the prediction accuracy. It provides reference for researching the real estate price index prediction.