英文摘要 |
This study used artificial intelligence deep learning technology to forecast the real estate trends in Taiwan. Economic variables, internet search volume, and demographic variables are utilized to forecast the real estate market. Furthermore, the real estate market trends were predicted based on the Long Short-Term Memory (LSTM) model and the accuracy of the predictions was evaluated using the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model. The results reveal that the LSTM model predicted the Taiwan real estate market better than the GARCH model, thus verifying the feasibility of the LSTM model in forecasting the trend of real estate markets. Furthermore, a rolling window was used to adjust the parameters of the LSTM model annually. Therefore, the prediction accuracy of Taiwan’s house price and transaction volume indices improved to 97% and 76%, respectively, thereby enhancing its model prediction ability. Moreover, adjusting the rolling window also enabled the advancements over time; therefore, the predicted results were closer to the practical situation. |