Transforming Japan Real Estate

TL;DR

This work addresses the challenge of locally predicting real estate performance in Japan by constructing a municipality-level price index from 2005 onward using MLIT transaction data and enriching it with long-horizon demographic and economic factors. It evaluates simple factor models and long-short strategies for each driver (population/migration, taxable income, and new dwellings) and demonstrates a Transformer-based time-series approach that achieves $R^2 = 0.28$ on risk-adjusted return forecasts over a 4-year horizon. The findings show that several alternative data signals generate statistically and economically meaningful returns with favorable risk-adjusted profiles, while spatial neighbors contribute limited predictive power. The results highlight the potential for integrating diverse data sources and advanced models to inform real estate investment decisions in Japan, though they also underscore the need for broader data gathering and factor expansion to improve accuracy and reliability.

Abstract

The Japanese real estate market, valued over 35 trillion USD, offers significant investment opportunities. Accurate rent and price forecasting could provide a substantial competitive edge. This paper explores using alternative data variables to predict real estate performance in 1100 Japanese municipalities. A comprehensive house price index was created, covering all municipalities from 2005 to the present, using a dataset of over 5 million transactions. This core dataset was enriched with economic factors spanning decades, allowing for price trajectory predictions. The findings show that alternative data variables can indeed forecast real estate performance effectively. Investment signals based on these variables yielded notable returns with low volatility. For example, the net migration ratio delivered an annualized return of 4.6% with a Sharpe ratio of 1.5. Taxable income growth and new dwellings ratio also performed well, with annualized returns of 4.1% (Sharpe ratio of 1.3) and 3.3% (Sharpe ratio of 0.9), respectively. When combined with transformer models to predict risk-adjusted returns 4 years in advance, the model achieved an R-squared score of 0.28, explaining nearly 30% of the variation in future municipality prices. These results highlight the potential of alternative data variables in real estate investment. They underscore the need for further research to identify more predictive factors. Nonetheless, the evidence suggests that such data can provide valuable insights into real estate price drivers, enabling more informed investment decisions in the Japanese market.

Figures (20)

• Figure 1: A subset of the categorical columns for transactions data
• Figure 2: Results of OLS regression
• Figure 3: Residential Price index for selected municipalities over time
• Figure 4: Cumulative net migration for selected municipalities
• Figure 5: Results of linear model for taxable income growth