AI-driven investment strategies: identifying the urban rent premium in Tokyo through the amenities magnet scores

Anett Wins et al.

Journal of Property Investment & Finance2026https://doi.org/10.1108/jpif-10-2025-0150article
AJG 1ABDC B
Weight
0.50

Abstract

Purpose This case study examines how structural, locational, and amenity attributes influence residential rents in Tokyo, one of the world's largest metropolitan areas. The scoring and modelling approach offer a scalable framework for identifying high-potential investment opportunities. Design/methodology/approach We introduce the Amenities Magnet Score© (AMS), an AI-enabled metric quantifying a location's attractiveness for metropilitan Tokyo based on 98,869 Points of Interest (POIs). AMS and its temporal evolution are computed on a 5,000-cell grid covering ∼189 km2. The higher the AMS, the better a location is supplied with amenities for residential living. This framework is refined by incorporating a Tokyo-specific Basic-Living-Need category, Proximity to Transit Hubs, reflecting the city's emphasis on a reliable and highly frequented commuting system. A Generalized Additive Model (GAM) with a spatial Gaussian-process smooth is fitted to 1.53 million rental listings to assess their non-linear response to static and dynamic AMS. Findings The GAM explains 91.5% of variation in log rents, confirming amenities as a fundamental determinant of rental values. AMS ranks as the fourth most influential predictor. We observe a convex–concave amenity response, with rent growth saturating beyond AMS ≈ 92. Mid-AMS zones (≈65–92) near secondary hubs exhibit the strongest growth potential, underscoring the strategic value of amenity-based investment targeting. Practical implications The results indicate that in Tokyo amenities and the Proximity to Transit Hubs are fundamental determinants of rental values, providing useful strategic implications for all real estate market participants. Originality/value AMS and BLN scores are calculated via an AI-driven, scalable algorithm tailored to Tokyo's urban dynamics. This research empirically validates amenity scoring as a tool for optimizing real estate investment strategies.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1108/jpif-10-2025-0150

Or copy a formatted citation

@article{anett2026,
  title        = {{AI-driven investment strategies: identifying the urban rent premium in Tokyo through the amenities magnet scores}},
  author       = {Anett Wins et al.},
  journal      = {Journal of Property Investment & Finance},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1108/jpif-10-2025-0150},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

AI-driven investment strategies: identifying the urban rent premium in Tokyo through the amenities magnet scores

Flags are reviewed by the Arbiter methodology team within 5 business days.


Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.