Taiwan Consumer Spending
Taiwan · Quarterly series · EC-TW-CS
Latest, Q2 2026
2.98T TWD
+0.3% from Q1 2026
Forecast
Forecast for Q2 2027: 3.04T TWD, with an 80% interval of 2.84T TWD to 3.20T TWD.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| Q3 2026 | 2.99T TWD | 2.90T TWD | 3.07T TWD |
| Q4 2026 | 3.01T TWD | 2.73T TWD | 3.24T TWD |
| Q1 2027 | 3.03T TWD | 2.75T TWD | 3.25T TWD |
| Q2 2027 | 3.04T TWD | 2.84T TWD | 3.20T TWD |
AI confidence
Mixed evidenceThe tests show no consistent, material advantage over the no-change baseline.
Model: Agentic Investor TSFM (foundation model)
- Accuracy vs naive
- +7%Matches the no-change baseline over 8 tests (8 tests, 5 won)
- Direction
- 78%No clear edge over a coin flip (25 of 32 calls right in 8 tests)
- Turning points
- n/aToo few tests (7 turns, 8 needed) (7 turns in 8 tests, 2 without a turn)
- Error vs baseline
- 7% lowerError ratio 0.93; 1.00 is a tie.
- Tests won
- 5 / 8Complete rolling backtests; ties count as no win.
- Test period
- 2018-09-01 to 2026-06-014 observations ahead per test.
- 80% band coverage
- 88%Observed outcomes inside the band across all stored test windows.
- Band coverage uses all stored test windows, including model-selection windows when present; it does not determine the confidence label.
- Evaluated 2026-11-15 against the cached history through 2026-06-01.
- This is an evaluation of the serving model; it does not establish a winner across four model classes.
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.
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 97% of the 39 earlier readings since Q3 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| Q2 2026 | 2.98T TWD |
| Q1 2026 | 2.97T TWD |
| Q4 2025 | 2.99T TWD |
| Q3 2025 | 2.86T TWD |
| Q2 2025 | 2.81T TWD |
| Q1 2025 | 2.84T TWD |
| Q4 2024 | 2.89T TWD |
| Q3 2024 | 2.83T TWD |
| Q2 2024 | 2.79T TWD |
| Q1 2024 | 2.70T TWD |
| Q4 2023 | 2.69T TWD |
| Q3 2023 | 2.68T TWD |
| Q2 2023 | 2.65T TWD |
| Q1 2023 | 2.61T TWD |
| Q4 2022 | 2.57T TWD |
| Q3 2022 | 2.45T TWD |
| Q2 2022 | 2.35T TWD |
| Q1 2022 | 2.45T TWD |
| Q4 2021 | 2.48T TWD |
| Q3 2021 | 2.28T TWD |
| Q2 2021 | 2.27T TWD |
| Q1 2021 | 2.43T TWD |
| Q4 2020 | 2.41T TWD |
| Q3 2020 | 2.41T TWD |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Taiwan Consumer Spending in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators