基于PCA-ELM对辽宁省某市房价的预测

In order to predict the price of residential commercial housing in Shenyang, Liaoning Province quickly and accurately, economy, region, supply and demand were selected as the influencing factors, principal component analysis (PCA) dimension-reduction results were used as the input vector of ELM, and commercial residential housing price in Shenyang was used as the output vector of ELM. The data from 2010 to 2019 were used as training samples to train the established ELM model, and the training set was optimized by the leave-one cross-validation method, and the determination coefficient and relative error were used to evaluate the prediction results. The results show that the principal components extracted by PCA fully consider the incompleteness of influencing factors, and contain more than 91.56% information, which reduces information redundancy. Using PCA processed data to reduce the complexity of ELM calculation; The PCA-ELM model can be used to forecast the price of residential commercial housing effectively.