Portugal House Price Index

Portugal · Quarterly series · EC-PT-HPI

Latest, Q2 2026

301.4 pts

+3.6% from Q1 2026

Open interactive chartPortugal House Price Index in the app

358225.192.25Q1 2008Q2 2027
History through Q2 2026, the forecast path to Q2 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for Q2 2027: 339.0 pts, with an 80% interval of 320.1 pts to 358.0 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
Q3 2026311.3 pts307.1 pts316.3 pts
Q4 2026320.1 pts313.4 pts327.6 pts
Q1 2027329.6 pts313.7 pts347.2 pts
Q2 2027339.0 pts320.1 pts358.0 pts

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-14.

AI confidence

Supported evidence

The point forecast beat the no-change baseline overall and in a majority of the evaluated tests.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
+68%Beats the no-change baseline over 8 tests (8 tests, 8 won)
Direction
97%Beats a coin flip (31 of 32 calls right in 8 tests)
Turning points
n/aToo few tests (1 turn, 8 needed) (1 turn in 8 tests, 7 without a turn)
Error vs baseline
68% lowerError ratio 0.32; 1.00 is a tie.
Tests won
8 / 8Complete rolling backtests; ties count as no win.
Test period
2018-09-01 to 2026-06-014 observations ahead per test.
80% band coverage
84%Observed outcomes inside the band across all stored test windows.
How this assessment is made

AI confidence describes historical evidence for this forecast, not a probability of being correct. Each backtest fits on data available before its test window. The baseline carries the last value forward. Supported evidence requires at least six complete, non-overlapping tests, an error ratio below 0.90 (rounded to two decimals), and wins in a majority of tests. Ratios from 0.90 to below 1.10 are on par; 1.10 or above is weak evidence. Inconsistent wins produce mixed evidence. For a selected model, only the recent tests excluded from model selection determine this label. These are historical simulations using the available data, not a live trading track record; revisions and foundation-model pretraining can limit how closely they reproduce a past decision. Past performance can change.

Replay past tests

Model comparison

Comparison pendingA new ticker first receives its serving model's forecast and evaluation. An eligible nightly batch can compare both candidates, subject to call budgets and retry limits.

Reading

That is the highest of the 40 readings since Q3 2016.

Written from the figures by a fixed template; no AI model is involved.

Recent history (24 observations)
The 24 most recent observations, newest first.
PeriodValue
Q2 2026301.4 pts
Q1 2026291.0 pts
Q4 2025280.2 pts
Q3 2025269.4 pts
Q2 2025258.8 pts
Q1 2025247.1 pts
Q4 2024235.7 pts
Q3 2024228.9 pts
Q2 2024220.7 pts
Q1 2024212.4 pts
Q4 2023211.3 pts
Q3 2023208.5 pts
Q2 2023204.7 pts
Q1 2023198.6 pts
Q4 2022195.9 pts
Q3 2022193.8 pts
Q2 2022188.3 pts
Q1 2022182.6 pts
Q4 2021176.0 pts
Q3 2021171.3 pts
Q2 2021166.4 pts
Q1 2021161.7 pts
Q4 2020157.7 pts
Q3 2020153.6 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Portugal