Returns predictor · v0 beta

Projected returns by community — price trend, mean reversion, confidence band

Every Abu Dhabi community with a published price trend, projected over 12 / 36 / 60 months from that trend, mean-reverted toward a long-run anchor, with an explicit confidence band on every number. Communities with no trend of their own are left out rather than filled in with a city average. No black box: the drift, the reversion and the band are all shown.

Beta · baseline layer only. The model has three layers: a mean-reverting baseline drift from each community's own price history, per-event infrastructure shocks, and off-plan supply pressure. Right now only the baseline layer is live for Abu Dhabi. The infrastructure event set — the dated, source-cited list of rail, airport and mega-development milestones with their catchments — has not been built for the emirate yet, so every projection below is trend and reversion alone, with no shock applied. Note that Abu Dhabi has no metro network; when the event set lands it will be rail, airport and mega-development events, not transit stations. Full methodology

8 communities projected · baseline trend only · 34 excluded, no price trend

#	Community	Projected 36m	Band	Z-score
1	Yas Island	+31.5%	±7.5pp	+0.55
2	Saadiyat Island	+31.5%	±7.5pp	+0.55
3	Al Reem Island	+31.5%	±7.5pp	+0.55
4	Masdar City	+31.5%	±7.5pp	+0.55
5	Al Reef	+31.5%	±7.5pp	+0.55
6	Al Samha	+31.5%	±7.5pp	+0.55
7	Al Ghadeer	+29.0%	±7.5pp	-1.05
8	Al Raha Beach	+27.1%	±7.5pp	-2.25

Methodology

Projection formula. For each community, the projected total PSF return over the horizon is the sum of three terms — a mean-reverting baseline drift, per-event infrastructure shocks, and an off-plan supply-pressure drag.

Baseline + mean reversion. Drift is annualised from the community's last eight quarters of ADREC price history where that series exists, and from its published headline YoY benchmark otherwise. Either way it is clamped to [-6%, +12%]/yr — which is why several communities currently sit at the same clamped ceiling. The clamped value is then blended toward a 7%/yr Abu Dhabi long-run anchor — λ = 0.1 at 12m, 0.3 at 36m, 0.5 at 60m. This stops a community currently in a hot streak from compounding that streak out to five years; markets revert. Communities with neither a quarterly series nor a published YoY are excluded from the table rather than projected from the city anchor alone.

Infrastructure shocks (not yet active). No Abu Dhabi infrastructure event set is published, so this term currently contributes zero to every projection. When it is built, each event (rail, airport, mega-development) carries a peak uplift coefficient, a ramp-up window before opening day, a saturation window after opening, and a catchment radius. The contribution to a given community is the peak uplift × distance decay × time factor × confidence weight. Distance decay is linear from 1.0 at the event centre to 0.0 at the catchment boundary. The time factor is the average value of the shock curve over the horizon window, integrated numerically.

Supply pressure (not yet active). Per-community off-plan share is not published for Abu Dhabi yet, so this term also contributes zero today. The mechanism, once the share exists: city baseline 30%, communities above it take a small negative drag scaled by the excess percentage points and the horizon length, capped at -3pp — heavy unbuilt pipelines create absorption pressure when those units complete and hit the secondary market.

Confidence band. Each projection ships with a symmetric ± band that combines a calibration-uncertainty term (large while coefficients are literature defaults) and a per-year horizon-uncertainty term. Longer horizons widen the band; communities with more shocks applied widen it further.

Z-score normalisation. The Z-score column expresses each community's projection as standard deviations above or below the cohort mean for the same horizon, so picks can be ranked relative to peers.

What v0 doesn't model yet. Service-charge trajectory, foreign-buyer demand proxies, and per-building granularity (currently community-level only). Supply pressure uses the offplan_pct proxy rather than per-project unit counts because the project-level data is too sparse on completion dates. v1 calibration plan: run scripts/calibrate/predictor-coefficients.ts against the pre-2020 ADREC back-fill to replace literature defaults with Abu Dhabi-specific values.

Source files for audit. Math: src/lib/predictor.ts. Coefficients: src/lib/predictor-coefficients.ts. Infrastructure events: src/data/infrastructure-pipeline.json. Every coefficient is auditable; no values are hidden behind a logo.