arxiv: 2603.00422 · v3 · submitted 2026-02-28 · 📊 stat.AP · q-fin.ST

Recognition: 1 theorem link

· Lean Theorem

Coupled Supply and Demand Forecasting in Platform Accommodation Markets

Harrison Katz

Authors on Pith no claims yet

Pith reviewed 2026-05-15 18:58 UTC · model grok-4.3

classification 📊 stat.AP q-fin.ST

keywords supply demand couplingaccommodation forecastingendogenous stock-out censoringplatform marketstourism forecastingtwo-sided marketsjoint forecastingrevenue management

0 comments

The pith

Booking models that ignore elastic supply in platform rentals learn regime-specific ceilings that break under policy changes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Standard tourism demand forecasting treats accommodation supply as fixed or exogenous. In short-term rental platforms, supply is elastic and co-evolves with demand through pricing and interventions, so realized bookings are always censored at the minimum of demand and supply. Models that omit this coupling learn ceilings tied to the observed regime and lose accuracy when supply shifts or policies intervene. The paper reframes the problem as endogenous stock-out censoring and outlines a three-part coupling framework to address it. A reader would care because forecasts used for revenue management or regulation become unreliable without joint modeling of the two sides.

Core claim

Realized booked nights satisfy B_{k,t} <= min(D_{k,t}, S_{k,t}), so booking models that ignore supply learn a regime-specific ceiling and become fragile under policy changes and supply shocks. The paper synthesizes literature across tourism forecasting, revenue management, two-sided markets, and Bayesian time series; develops a three-part coupling framework covering behavioral, informational, and intervention channels; and demonstrates the identification failure with a toy simulation before proposing a research agenda for jointly forecasting supply, demand, and their compositions.

What carries the argument

Endogenous stock-out censoring, where observed bookings are bounded by the minimum of latent demand and latent supply, together with the three-part coupling framework that links behavioral responses, informational design, and platform interventions.

If this is right

Joint supply-demand models remain accurate across different market regimes instead of locking onto the training-period ceiling.
The behavioral, informational, and intervention channels in the coupling framework can be used to recover demand parameters that would otherwise be unidentified.
Forecasts for revenue management and regulatory interventions become more robust once supply elasticity is modeled explicitly.
A research agenda focused on coupled forecasting replaces separate supply and demand pipelines in platform settings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same censoring logic would apply to other two-sided platforms where capacity on one side adjusts quickly to observed demand.
Without real-data validation, the size of the robustness gain from coupling remains unknown and could be tested by comparing historical forecast errors before and after major policy shifts.
Revenue-management systems that optimize prices without supply feedback may systematically over- or under-book in elastic markets.

Load-bearing premise

That a conceptual three-part framework and a toy simulation suffice to show practical gains in identification without testing on real platform data.

What would settle it

A side-by-side comparison showing that a demand-only model trained in one supply regime produces large forecast errors after an observed supply shock or policy change, while a coupled model does not.

read the original abstract

Tourism demand forecasting is methodologically mature, but it typically treats accommodation supply as fixed or exogenous. In platform-mediated short-term rentals, supply is elastic, decision-driven, and co-evolves with demand through pricing, information design, and interventions. I reframe the core issue as endogenous stock-out censoring: realized booked nights satisfy B_{k,t} <= min(D_{k,t}, S_{k,t}), so booking models that ignore supply learn a regime-specific ceiling and become fragile under policy changes and supply shocks. This narrated review synthesizes work from tourism forecasting, revenue management, two-sided market economics, and Bayesian time-series methods; develops a three-part coupling framework (behavioral, informational, intervention); and illustrates the identification failure with a toy simulation. I conclude with a focused research agenda for jointly forecasting supply, demand, and their compositions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper correctly flags that platform booking data is censored by endogenous supply so standard demand models learn fragile ceilings, but it only demonstrates this with a synthesis and toy simulation.

read the letter

The core point is that realized bookings in short-term rental platforms satisfy B <= min(D, S), so models that ignore supply will pick up a regime-specific ceiling and fail when hosts adjust availability or prices shift. Katz makes this case by pulling together tourism forecasting, revenue management, and two-sided market ideas into a three-part coupling framework that separates behavioral, informational, and intervention channels. The synthesis is clean and the toy simulation illustrates the identification problem without much fuss. That reframing is useful because it turns a known limitation into a concrete research agenda for joint supply-demand forecasting. The literature connections are drawn from outside the author's own work and do not rely on self-fitted parameters. The main limitation is the absence of any real platform data or formal identification result. We see the logic and the simulation, but nothing shows whether the fragility is large relative to other misspecifications or whether existing censored estimators already handle most of it. The central claim about policy-change fragility therefore stays plausible rather than demonstrated. This is for researchers working on applied forecasting in accommodation platforms or other two-sided markets who want a structured way to think about supply endogeneity. A reader looking for a finished empirical paper will be disappointed, but someone building a research program will get clear next steps. I would send it to peer review. The idea is worth referee time even though it needs empirical validation and comparisons to existing methods.

Referee Report

3 major / 2 minor

Summary. The paper claims that tourism demand forecasting in platform accommodation markets must account for endogenous supply because realized bookings satisfy B_{k,t} ≤ min(D_{k,t}, S_{k,t}), causing models that ignore supply to learn regime-specific ceilings and become fragile under policy changes and supply shocks. It synthesizes literature from tourism forecasting, revenue management, two-sided market economics, and Bayesian time-series methods; develops a three-part coupling framework (behavioral, informational, intervention); illustrates the identification failure with a toy simulation; and concludes with a research agenda for jointly forecasting supply, demand, and their compositions.

Significance. If the central reframing holds, the work could meaningfully advance forecasting practice in two-sided platforms by highlighting endogenous censoring as a source of fragility. The cross-literature synthesis is a clear strength, and the toy simulation usefully illustrates the conceptual point. However, the absence of real-data validation or formal identification results limits the assessed practical significance to a call for future research rather than a demonstrated improvement.

major comments (3)

[Toy simulation] Toy simulation section: The simulation illustrates the conceptual identification failure when supply is ignored but provides no quantification of bias magnitude, no comparison against existing censored-demand estimators from the revenue management literature, and no exploration under realistic supply elasticities; this leaves open whether the fragility is first-order relative to other misspecifications.
[Coupling framework] Framework section: The three-part coupling framework is presented narratively without formal mathematical specification, estimation procedure, or identification conditions under which joint supply-demand parameters can be recovered from observed bookings; this makes it difficult to evaluate how the framework resolves the stock-out censoring problem in practice.
[Conclusion / research agenda] Empirical validation: The central claim that ignoring supply produces fragile forecasts under policy changes and supply shocks rests entirely on the toy simulation and literature synthesis; without at least one real platform dataset application or out-of-sample robustness check, the practical relevance of the reframing cannot be assessed.

minor comments (2)

[Abstract] Abstract: The phrasing 'I conclude with a focused research agenda' is appropriate for a review-style manuscript but could be expanded to preview one or two concrete open questions that the framework raises for statistical estimation.
[Framework] Notation: The indexing k,t for bookings, demand, and supply is introduced clearly but should be restated at the start of the framework section to ensure consistency for readers.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for the constructive comments, which help clarify the positioning and scope of our narrated review. We address each major comment below, proposing targeted revisions where feasible while remaining honest about the manuscript's conceptual focus.

read point-by-point responses

Referee: [Toy simulation] Toy simulation section: The simulation illustrates the conceptual identification failure when supply is ignored but provides no quantification of bias magnitude, no comparison against existing censored-demand estimators from the revenue management literature, and no exploration under realistic supply elasticities; this leaves open whether the fragility is first-order relative to other misspecifications.

Authors: We agree that the toy simulation can be strengthened to better quantify the issue. In the revised manuscript we will expand the section to report explicit bias magnitudes, include comparisons against standard censored regression estimators from the revenue management literature, and add sensitivity checks across a range of realistic supply elasticities. These additions will help assess whether the identified fragility is first-order. revision: yes
Referee: [Coupling framework] Framework section: The three-part coupling framework is presented narratively without formal mathematical specification, estimation procedure, or identification conditions under which joint supply-demand parameters can be recovered from observed bookings; this makes it difficult to evaluate how the framework resolves the stock-out censoring problem in practice.

Authors: We accept this point. The revised version will include formal mathematical specifications for the behavioral, informational, and intervention components of the coupling framework, along with a discussion of candidate estimation procedures and identification conditions drawn from the synthesized Bayesian time-series and two-sided market literature. We will note that complete identification results remain an open empirical question. revision: yes
Referee: [Conclusion / research agenda] Empirical validation: The central claim that ignoring supply produces fragile forecasts under policy changes and supply shocks rests entirely on the toy simulation and literature synthesis; without at least one real platform dataset application or out-of-sample robustness check, the practical relevance of the reframing cannot be assessed.

Authors: We agree that real-data validation would strengthen practical claims. However, the manuscript is explicitly positioned as a narrated review and research agenda rather than an empirical demonstration. Proprietary platform data access and the scope of a full application lie outside the current work. We will revise the conclusion to more explicitly frame the contribution as problem identification and agenda-setting while acknowledging the simulation-based evidence as illustrative only. revision: partial

standing simulated objections not resolved

Conducting a real platform dataset application or out-of-sample robustness check, which would require proprietary data and constitute a separate empirical study beyond the scope of this review.

Circularity Check

0 steps flagged

No circularity: synthesis and toy illustration rest on external literatures without self-referential reduction.

full rationale

The paper reframes realized bookings via the definitional inequality B_{k,t} <= min(D_{k,t}, S_{k,t}), synthesizes external work across tourism forecasting, revenue management, and two-sided markets, introduces a three-part coupling framework, and illustrates identification failure via toy simulation. No load-bearing step reduces by construction to a fitted parameter, self-citation, or ansatz imported from the author's prior work. The central claim follows directly from the standard supply-demand identity rather than any looped derivation. This is a review and agenda-setting manuscript whose content is independent of its own outputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central reframing rests on the domain assumption that supply is elastic and co-evolves with demand through pricing and information; no free parameters or invented entities are introduced in the abstract.

axioms (1)

domain assumption Supply in platform accommodation markets is elastic, decision-driven, and co-evolves with demand
Invoked to justify the stock-out censoring reframing and the need for joint modeling.

pith-pipeline@v0.9.0 · 5431 in / 1116 out tokens · 31659 ms · 2026-05-15T18:58:43.947881+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

realized booked nights satisfy Bk,t ≤ min(Dk,t, Sk,t)

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.