A long short-term memory model for forecasting housing prices in Taiwan in the post-epidemic era through big data analytics
Bibliographic record
Abstract
This study aims to analyse housing prices in Taiwan in the post-epidemic era, identify the crucial factors influencing them, and develop a suitable method for analysing and forecasting them. This study collects relevant data such as Taiwan's housing price index data from 2002 to 2020 to identify the crucial factors affecting Taiwan's housing prices; this is achieved by constructing a regression model, forecasting Taiwan's housing prices through a constructed long short-term memory (LSTM) model that employs big data analytics, and verifying the efficiency of the proposed models through R-square and root mean square error values. The results indicate that the top 10 factors affecting Taiwan's housing prices are mostly related to mortgage interest rates, suggesting that in Taiwan, the effect on housing prices in the post-epidemic era may be non-significant. This study collects data on Taiwan's housing price for the period from the first quarter of 2002 to the fourth quarter of 2020 to construct an LSTM for forecasting Taiwan's housing prices. The results indicate that the proposed LSTM exhibits good fitness, indicating that the model is suitable for analysing and forecasting housing prices. Given that analysing and forecasting quantity is also crucial in housing market analyses and that this study focuses only on predicting housing prices, future research should explore the simultaneous prediction and analysis of both price and quantity.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".