Comparison and Optimization Strategies of Airbnb Rental Prediction Models: An Empirical Study Based on Linear Regression, XGBoost and Random Forest
Bibliographic record
Abstract
As a leading short-term rental platform in the sharing economy, Airbnb employs dynamic pricing based on multiple factors, posing challenges for accurate rental price prediction. This study aims to improve rental price prediction by comparing and optimizing three machine learning models—linear regression, random forest, and XGBoost—using Airbnb listing data. We develop a multi-model prediction framework that exploits each model’s strengths: linear regression provides interpretability of key features, random forest captures nonlinear interactions, and XGBoost applies gradient-boosting techniques to minimize error. Using standard regression metrics (e.g., RMSE, MAPE) for evaluation, we find that XGBoost delivers the highest predictive accuracy (≈8% error), outperforming the random forest and linear regression models. The results indicate that XGBoost’s enhanced ability to model complex market dynamics yields more reliable price estimates, whereas the baseline linear model and random forest show higher errors and signs of overfitting. In conclusion, our comparative analysis offers practical insights for stakeholders: hosts can leverage the improved model for optimal pricing strategies to maximize revenue and occupancy rates, the Airbnb platform can refine its smart pricing tool for greater market efficiency, and overall data-driven pricing strategies benefit the sharing economy by aligning stakeholder interests.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".