% ============================================================================
\section{Introduction}
\label{sec:introduction}
% ============================================================================

The hedonic price framework decomposes the market value of a heterogeneous good
into the implicit prices of its characteristics \citep{lancaster1966new,
rosen1974hedonic}. In housing markets it remains the workhorse tool for appraisal,
index construction, property-tax assessment, and policy analysis. Yet the empirical
performance of hedonic models is bounded by the richness of the characteristics an
analyst can measure. A large share of what determines a home's value---its state of
repair, the quality of its finishes, its curb appeal, the character of its
street---is recorded not in structured fields but in the free-text description and
the photographs that accompany each listing. These modalities have historically been
discarded because they were costly to encode at scale, leaving hedonic estimates
exposed to omitted-quality bias and hedonic predictions short of their potential
accuracy.

This paper treats general-purpose artificial-intelligence models as a
\emph{feature-engineering technology} for hedonic analysis, and quantifies the
explanatory power that technology adds. We assemble a cross-section of 19{,}123
single-family houses and townhouses listed for sale in Quebec, pooling the
brokerage-listed MLS inventory from Realtor.ca with the for-sale-by-owner inventory
from DuProprio. On top of standard structural, locational, and amenity attributes,
we build two machine-generated feature layers. First, a large language model (LLM)
reads each free-text description and returns a fixed set of property
specifications---state of repair, renovation of the kitchen and bathroom, flooring
and countertop materials, heating system, view, and income potential---under a
strict JSON schema that guarantees valid, reproducible output. Second, a
vision--language model inspects the façade photograph of each property and returns
objective visual attributes: overall condition, curb appeal, renovation level,
exterior materials, landscaping, setting, and a luxury indicator. Because both
extractions are schema-constrained, deterministic, and blind to the listing price,
their outputs behave as ordinary tabulated regressors rather than as noisy text.

Our contribution is threefold. First, we show that AI-based feature engineering
delivers economically meaningful gains in explanatory power over an already rich
hedonic specification: the two machine-generated layers raise in-sample $R^2$ from
0.717 to 0.755 (nearly four points) in our preferred specification, and raise the
out-of-sample $R^2$ of every estimator we consider, with the façade-vision layer
alone contributing the largest single increment of any feature block (2.7 points for
gradient boosting, 5.8 points for OLS). Second, we show that the extracted
attributes carry interpretable implicit prices---a one-point increase in visual curb
appeal is associated with a 2.3\% higher asking price, a visible luxury cue with
5.2\%, brick or stone façades with premia of 3--4\% relative to vinyl siding, and a
renovated kitchen (read from the text) with 2.6\%---so the approach augments rather
than replaces the classical hedonic regression. Third, we document a complete,
reproducible pipeline from raw scraped listings to an analysis-ready dataset,
including rules-based outlier cleaning, unit harmonization that reconstructs living
area from room-level dimensions, and the schema-constrained extraction protocol,
with a total AI cost of about \$60 for the full sample---roughly a third of a cent
per listing.

Our main findings can be summarized as follows. A log--linear specification with 195
municipality fixed effects, property-type fixed effects, and
municipality-clustered standard errors explains 75.5\% of the variation in log
asking prices when living area is observed, and 72.5\% on the full sample when it is
not. The estimated implicit prices are economically sensible: the living-area
elasticity is 0.36, each additional bathroom is associated with a 7.6\% premium, and
the age profile traces the familiar depreciation-then-heritage pattern. The
municipality effects span a wide range---from roughly $+231$\% in Westmount to about
$-30$\% in remote municipalities---and order the province's markets as expected.
Benchmarking a ladder of estimators on the identical feature set, an ensemble blend
of a robust embedding-based neural network and gradient boosting attains an
out-of-sample $R^2$ of 0.779 with a median absolute prediction error of 14.0\%. We
interpret all estimates as \emph{predictive} associations rather than causal
effects, since listing content is chosen by sellers and correlates with unobserved
determinants of value, and we discuss the asking-price nature of the dependent
variable at length in Section~\ref{sec:robustness}.

Beyond the specific Quebec application, the exercise speaks to a general measurement
problem in housing economics. Text- and image-derived quality measures have until
now required bespoke supervised models trained on labeled data
\citep{nowak2017textual,shen2021information,johnson2020curb}. General-purpose
foundation models with schema-constrained decoding lower the fixed cost of that
measurement step to nearly zero, produce attributes that are human-readable rather
than latent, and can be audited field by field. Our results suggest that this
technology moves the effective characteristics frontier of hedonic analysis by
enough to matter for appraisal, automated valuation, and assessment applications.

The remainder of the paper is organized as follows. Section~\ref{sec:literature}
reviews the related literature. Section~\ref{sec:data} describes the data sources
and cleaning. Section~\ref{sec:methodology} presents the feature-engineering
pipeline and the econometric specification. Section~\ref{sec:results} reports the
main results. Section~\ref{sec:benchmark} maps the predictive frontier across
estimators. Section~\ref{sec:robustness} discusses robustness and limitations.
Section~\ref{sec:conclusion} concludes.