AgenticInvestor

Taiwan Services Inflation

Taiwan · Monthly series · EC-TW-SI

Latest, October 2026

2.2%

-0.26pp from September 2026

Open interactive chartTaiwan Services Inflation in the app

4.7351.828-1.08November 2016October 2027
History through October 2026, the forecast path to October 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for October 2027: 2.4%, with an 80% interval of 1.6% to 3.1%.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
November 20262.3%2.1%2.5%
December 20262.2%2.0%2.4%
January 20272.8%1.1%4.7%
February 20271.8%0.4%3.1%
March 20272.4%1.9%2.8%
April 20272.3%1.8%2.8%
May 20272.3%1.5%3.0%
June 20272.2%1.6%2.8%
July 20272.2%1.6%2.8%
August 20272.2%1.7%2.7%
September 20272.1%1.5%2.6%
October 20272.4%1.6%3.1%

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-15.

AI confidence

Mixed evidence

The tests show no consistent, material advantage over the no-change baseline.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
+4%Matches the no-change baseline over 12 tests (12 tests, 8 won)
Direction
64%No clear edge over a coin flip (90 of 140 calls right in 12 tests)
Turning points
71 of 83Anticipated most turns (83 turns in 12 tests, 0 without a turn)
Error vs baseline
4% lowerError ratio 0.96; 1.00 is a tie.
Tests won
8 / 12Complete rolling backtests; ties count as no win.
Test period
2014-11-01 to 2026-10-0112 observations ahead per test.
80% band coverage
80%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

It is above 64% of the 119 earlier readings since November 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
October 20262.2%
September 20262.5%
August 20262.5%
July 20262.6%
June 20262.9%
May 20262.5%
April 20262.3%
March 20262.2%
February 20263.5%
January 20260.9%
December 20252.3%
November 20252.2%
October 20252.4%
September 20252.0%
August 20252.2%
July 20252.2%
June 20251.9%
May 20252.1%
April 20252.0%
March 20252.1%
February 20250.9%
January 20253.4%
December 20242.2%
November 20242.3%

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Taiwan