AgenticChina GDP YoY
China · Quarterly series · ECONOMICS:CNGDPYY
Latest, Q3 2026
4.5%
+0.20pp from Q2 2026
Forecast
Forecast for Q3 2027: 5.1%, with an 80% interval of 2.2% to 7.9%.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| Q4 2026 | 4.9% | 3.1% | 6.7% |
| Q1 2027 | 4.7% | 2.3% | 7.1% |
| Q2 2027 | 5.1% | -2.0% | 12.2% |
| Q3 2027 | 5.1% | 2.2% | 7.9% |
AI confidence
Needs refreshThe data refresh is due. Confidence will be reassessed against the refreshed history.
Model: CatBoost (machine learning)
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
4 of 4 models evaluatedModels are selected on older tests and evaluated on separate recent tests. All four classes completed their backtests.
Models tested
CatBoost scored lowest on the 2 older tests (0.95) and was chosen. The 6 recent tests played no part in the choice and give its grade (1.06). The search for a model that beats the naive forecast on both sets of tests goes on. Scores are MASE: a model's errors divided by the naive forecast's, so 1 is a tie.
4 model classes completed the tests: Machine learning, Foundation model, Statistical, Neural network.
| Model | Class / library | Older tests | Recent tests | Role |
|---|---|---|---|---|
| CatBoost (machine learning) | Machine learning · MLForecast · CPU | 0.95 | 1.06 | Serving |
| Timestral (foundation model) | Foundation model · Timestral · GPU | 1.00 | 0.97 | Tested |
| AutoETS (statistical) | Statistical · StatsForecast · CPU | 1.00 | 1.44 | Tested |
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
| N-HiTS (neural network) | Neural network · NeuralForecast · CPU | 1.03 | 2.96 | Tested |
Reading
It is above 15% of the 39 earlier readings since Q4 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| Q3 2026 | 4.5% |
| Q2 2026 | 4.3% |
| Q1 2026 | 5.0% |
| Q4 2025 | 4.5% |
| Q3 2025 | 4.8% |
| Q2 2025 | 5.2% |
| Q1 2025 | 5.4% |
| Q4 2024 | 5.4% |
| Q3 2024 | 4.6% |
| Q2 2024 | 4.7% |
| Q1 2024 | 5.3% |
| Q4 2023 | 5.3% |
| Q3 2023 | 5.0% |
| Q2 2023 | 6.5% |
| Q1 2023 | 4.7% |
| Q4 2022 | 3.0% |
| Q3 2022 | 4.0% |
| Q2 2022 | 0.8% |
| Q1 2022 | 4.8% |
| Q4 2021 | 4.5% |
| Q3 2021 | 5.5% |
| Q2 2021 | 8.1% |
| Q1 2021 | 18.9% |
| Q4 2020 | 6.5% |
Source
Data: ECONOMICS feed via TradingView.
More from Agentic Investor
- Open China GDP YoY in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators