Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment

TL;DR

This study demonstrates that weekly sub-city price indices in Dubai can be forecast more accurately by integrating signals of urban development, market sentiment, and macro context with transaction histories. The authors construct 19 regional weekly indices from 2015–2025 data and evaluate forecasts across nine horizons using rolling time-series cross-validation, comparing nine multimodal configurations and several baselines. They find that sentiment and SAR signals primarily enhance long-horizon forecasts (26–34 weeks), reducing mean absolute error by about 35% relative to price-only models, with nonparametric learners (KNN, Random Forest) delivering the strongest gains. Semantic representations of sentiment outperform lexical tone, and SAR backscatter outperforms optical proxies, indicating that topical structure and structural changes precede price movements. Overall, the results establish benchmarks for weekly sub-city index forecasting and show that multimodal fusion yields meaningful, regionally consistent improvements for strategic planning.

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 across regions. Nonparametric learners consistently outperform deep architectures in this data regime. These findings establish benchmarks for weekly sub-city index forecasting and demonstrate that remote sensing and news sentiment materially improve predictability at strategically relevant horizons.

Figures (11)

• Figure 1: Weekly price indices for 19 Dubai sub-city regions (2015--2025, rebased to 100). Regional trajectories diverge substantially from the citywide aggregate (bold).
• Figure 2: Overview of the multimodal forecasting framework integrating transaction data, news sentiment, SAR imagery, and interest rates for sub-city price index prediction.
• Figure 3: Spatial distribution of selected Master Projects in Dubai.
• Figure 4: Quantile trimming diagnostics for transaction-based index construction. Relaxed trimming ([5th, 95th]) improves citywide cycle fidelity relative to a macro benchmark, while more aggressive trimming ([25th, 85th]) yields a smoother regional monitoring signal with reduced sensitivity to idiosyncratic transactions.
• Figure 5: Sentiment feature diagnostics. (a) Weekly NSI captures market sentiment shifts including the COVID-19 period. (b) Low correlation between lexical NSI features and semantic PCA components confirms complementary information.