Research and Application of Second-Hand Housing Price Prediction Model Based on LSTM

The price of second-hand houses has always been a matter of great concern to people. This paper collects the sales data of second-hand houses in Jinshui District of Zhengzhou City, assigns spatial sequence to the data through spatial autocorrelation analysis and design algorithm, constructs LSTM model combining spatial sequence and attention mechanism, and forecasts the price of second-hand houses in Jinshui District. Finally, three schemes are designed and compared based on LSTM neural network. Experimental results verify that the LSTM model combining spatial sequence and attention mechanism constructed in this paper has better prediction effect.