UQO Working Paper No. 5 — Airbnb, residential rents and housing market pressure.
1\begin{tabular}{lcccc}2\toprule3Model & $R^2$ (mean) & $R^2$ (s.d.) & RMSE & MAE \\4\midrule5\multicolumn{5}{l}{\textit{Random 5-fold}} \\6OLS & 0.4767 & 0.0405 & 0.2256 & 0.1737 \\7LASSO & 0.4767 & 0.0406 & 0.2256 & 0.1737 \\8Elastic Net & 0.4767 & 0.0405 & 0.2256 & 0.1737 \\9Random Forest & 0.6473 & 0.0445 & 0.1849 & 0.1343 \\10Gradient Boosting & 0.6538 & 0.0334 & 0.1834 & 0.1340 \\11\addlinespace12\multicolumn{5}{l}{\textit{Spatial 5-fold (FSA blocks)}} \\13OLS & 0.4667 & 0.0539 & 0.2261 & 0.1752 \\14LASSO & 0.4668 & 0.0538 & 0.2261 & 0.1752 \\15Elastic Net & 0.4668 & 0.0538 & 0.2261 & 0.1752 \\16Random Forest & 0.4307 & 0.1594 & 0.2306 & 0.1803 \\17Gradient Boosting & 0.4140 & 0.1076 & 0.2355 & 0.1842 \\18\addlinespace19\bottomrule20\end{tabular}21\parbox{\textwidth}{\footnotesize Five-fold cross-validation of the models in Table~\ref{tab:ml_performance} on the same features and sample. Random folds shuffle listings; spatial folds assign whole forward sortation areas (181 FSA groups) to folds, so no test listing shares a neighbourhood with a training listing. Metrics are averaged over the five test folds; $R^2$ (s.d.) is the standard deviation across folds.}22