Paper: arXiv 2403.00273

Authors: Iván Belenky

Abstract

The Argentinian real estate market presents a unique case study characterized by its unstable and rapidly shifting macroeconomic circumstances over the past decades. Despite the existence of a few datasets for price prediction, there is a lack of mixed modality datasets specifically focused on Argentina. In this paper, the first edition of ARED is introduced. A comprehensive real estate price prediction dataset series, designed for the Argentinian market. This edition contains information solely for Jan-Feb 2024. It was found that despite the short time range captured by this zeroth edition (44 days), time dependent phenomena has been occurring mostly on a market level (market as a whole). Nevertheless future editions of this dataset, will most likely contain historical data. Each listing in ARED comprises descriptive features, and variable-length sets of images.

Complexity vs Empirical Score

  • Math Complexity: 0.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper is a dataset publication with no mathematical models or derivations, but it includes detailed data scraping methodology, visualization of statistical metrics (Wasserstein distance, quantile ranges), and a plan for future updates, making it highly implementation-heavy and ready for backtesting.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Argentine Real Estate Dataset Creation"] --> B["Methodology<br>Data Collection Jan-Feb 2024"]
  B --> C["Input Data<br>Property Listings + Images"]
  C --> D["Computational Process<br>Mixed Modality Data Aggregation"]
  D --> E["Key Finding 1<br>Market-Level Time-Dependent Phenomena"]
  D --> F["Key Finding 2<br>Lack of Historical Data"]
  E --> G["Outcome<br>ARED: First Edition Dataset"]
  F --> G

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper introduces ARED, the first edition of a comprehensive multimodal real estate price prediction dataset for the Argentinian market.

Source sentence
In this paper, the first edition of ARED is introduced. A comprehensive real estate price prediction dataset series, designed for the Argentinian market.

Assumes

No explicit assumptions found in the text.

Data

  • ARED · Ivan Belenky (author) other public
    Jan-Feb 2024 · Argentinian real estate listings
    Source sentence
    This edition contains information solely for Jan-Feb 2024. The onset date for its creation is mid-january 2024 (11th).

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • Despite the short 44‑day coverage, time‑dependent phenomena are observed primarily at the market level rather than at individual listings. statistical
    Source sentence
    It was found that despite the short time range captured by this zeroth edition (44 days), time dependent phenomena has been occurring mostly on a market level (market as a whole).
  • The Wasserstein distance between house and apartment price distributions remains constant over time, indicating that price drops occur cohesively across property types. statistical
    Source sentence
    This would indicate that when the market is dropping, it drops cohesively. Also, given the reduction in the nominal value of the Wasserstein distance itself it could be argued that once again, all habitable spaces are more equal to each other in terms of relative valuation, reinforcing the idea that prices can only drop as a cohesive whole.
  • Future editions of ARED will be released quarterly and will include historical data preceding January 11, 2024 to provide longer‑term market context. other
    Source sentence
    FUTURE OF ARED ARED commits to regular updates, with new editions scheduled to be released on a quarterly basis, next one expected on mid May 2024. In addition to updating the dataset with fresh data, there are plans to enrich ARED by including historical data preceding the 11th of January 2024.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 11 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

https://github.com/ivanbelenky/ARED — the authors' own repository

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (8)

  1. El origen de la dolarizaci 'o n inmobiliaria en la Argentina (2013)
  2. Property Listings for 5 South American Countries (2020)
  3. ST-RAP: A Spatio-Temporal Framework for Real Estate Appraisal (2023)
  4. Vision-based Real Estate Price Estimation (2017) — link
  5. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting (2021)
  6. A Contextual Master-Slave Framework on Urban Region Graph for Urban Village Detection (2023) — link
  7. Spatial-temporal transformer networks for traffic flow forecasting (2020) — link
  8. Informer: Beyond efficient transformer for long sequence time-series forecasting (2021)

0 of 8 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.