![[2602.18572] Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.18572] Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment
Summary
This article explores the forecasting of sub-city real estate price indices on a weekly basis by integrating satellite radar data and news sentiment analysis, demonstrating significant improvements in predictive accuracy.
Why It Matters
As real estate markets become increasingly volatile, accurate and timely price indicators are crucial for investors and policymakers. This research introduces a novel approach that combines satellite technology and sentiment analysis, offering a more granular view of market dynamics at the neighborhood level, which can enhance decision-making processes in urban planning and investment strategies.
Key Takeaways
- Combining satellite radar data with news sentiment improves real estate price forecasting.
- The study constructs weekly price indices for 19 sub-city regions in Dubai using extensive transaction data.
- Forecast accuracy varies significantly with time horizons; sentiment and radar data become critical beyond 14 weeks.
- Nonparametric models outperform deep learning architectures in this forecasting context.
- This research sets benchmarks for future studies in sub-city price index forecasting.
Computer Science > Machine Learning arXiv:2602.18572 (cs) [Submitted on 20 Feb 2026] Title:Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment Authors:Baris Arat, Hasan Fehmi Ates, Emre Sefer View a PDF of the paper titled Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment, by Baris Arat and 2 other authors View PDF HTML (experimental) Abstract:Reliable real estate price indicators are typically published at city level and low frequency, limiting their use for neighborhood-scale monitoring and long-horizon planning. We study whether sub-city price indices can be forecasted at weekly frequency by combining physical development signals from satellite radar with market narratives from news text. Using over 350,000 transactions from Dubai Land Department (2015-2025), we construct weekly price indices for 19 sub-city regions and evaluate forecasts from 2 to 34 weeks ahead. Our framework fuses regional transaction history with Sentinel-1 SAR backscatter, news sentiment combining lexical tone and semantic embeddings, and macroeconomic context. Results are strongly horizon dependent: at horizons up to 10 weeks, price history alone matches multimodal configurations, but beyond 14 weeks sentiment and SAR become critical. At long horizons (26-34 weeks), the full multimodal model reduces mean absolute error from 4.48 to 2.93 (35% reduction), with gains statistically significant a...
