TeX 62.3%
Python 37.6%
1\section{Data and institutional context}\label{sec:data}23The data are those of WP22, used read-only: the Vrai Prix snapshot of 21 October 2026 of Quebec land-registry deeds republished by the Journal de Québec / Journal de Montréal feed, geocoded and matched to the provincial assessment roll (769{,}995 registered sales from 4 January 2021 to 7 October 2026), reduced by the WP22 exclusion ledger to a headline population of \NSales{} house, condominium and plex sales with roll characteristics. The institutional facts that matter for forecasting are three. Deeds are published with a lag of ten to thirteen days and never backfilled (WP22 measured this on four earlier extractions), so the information set at an origin is the set of sales dated at least ten days before the publication date; the last complete month is September 2026 and October is partial. The roll is a single current vintage, so characteristics are post-sale for most dwellings; this affects Task~A in the same way for every model. The provider collects no sale below \$50{,}000.45Table~\ref{tab:variables} lists the variables actually available after inspection. The quality variables are floor area, lot area, year built, storeys, building genre, physical link (detached, semi-detached, row, integrated), number of dwellings for plexes, coordinates, municipality, MRC and region, and the assessment in force at the sale; bedrooms, bathrooms, parking, basement, condition, renovations, quality grade and listing attributes are not observed, and no image or text features are used. WP22 provides, in addition, the nested metric location cells and the feature engineering (imputation with time-stable missingness indicators, centred log areas, age bins) that we reuse unchanged, and two index products: the retrospective SHARP-HPI panel (province, 17 regions, 103 MRCs, 1{,}125 municipalities $\times$ three classes $\times$ 69 months), which serves only as the \emph{target} of Task~B, and the real-time vintage database (monthly publication dates from July 2022, filtered and smoothed modes, province, regions and the 64 municipalities with at least 1{,}500 sales), which is the only index information admitted as a \emph{predictor}.67\input{tables/tab_variables}89Table~\ref{tab:coverage} summarises coverage by region and class and the evaluation samples of each task. Figure~\ref{fig:map_density} maps municipal sales density. The sample is short for monthly forecasting: 69 months in total, of which the first 24 are history before the first origin; this constrains every model and is discussed throughout.1011\input{tables/tab_coverage}12\input{tables/tab_selection}1314Table~\ref{tab:selection_rates} quantifies selection into transaction directly: the annual sale rate of the roll stock is \SaleRatehouseageOne\% for the newest quintile of houses against \SaleRatehouseageThree{} to \SaleRatehouseageFive\% for older ones, and \SaleRatehousefaOne\% for the smallest quintile against \SaleRatehousefaFive\% for the largest. Sold dwellings are newer and smaller than the stock; the Task~A evaluation population is the dwellings that come to market, and every model is evaluated on that population.1516\input{tables/tab_selection_rates}1718\begin{figure}[htbp]\centering19\includegraphics[width=0.9\textwidth]{figures/fig_map_density.pdf}20\caption{Municipal sales density (headline sample, 2021--2026) and the 64 municipalities with real-time index vintages (outlined).}\label{fig:map_density}21\end{figure}22