Singapore Consumer Price Index
Singapore · Monthly series · EC-SG-CPI
Latest, September 2026
103.5 pts
+0.2% from August 2026
Forecast
Forecast for September 2027: 105.3 pts, with an 80% interval of 103.2 pts to 107.4 pts.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| October 2026 | 103.3 pts | 102.8 pts | 104.0 pts |
| November 2026 | 103.7 pts | 103.3 pts | 104.1 pts |
| December 2026 | 103.9 pts | 103.5 pts | 104.4 pts |
| January 2027 | 103.7 pts | 103.0 pts | 104.4 pts |
| February 2027 | 104.2 pts | 103.2 pts | 105.2 pts |
| March 2027 | 104.4 pts | 103.6 pts | 105.2 pts |
| April 2027 | 104.1 pts | 102.9 pts | 105.4 pts |
| May 2027 | 104.6 pts | 102.9 pts | 106.3 pts |
| June 2027 | 104.7 pts | 103.3 pts | 106.1 pts |
| July 2027 | 104.5 pts | 102.2 pts | 106.9 pts |
| August 2027 | 105.0 pts | 102.7 pts | 107.4 pts |
| September 2027 | 105.3 pts | 103.2 pts | 107.4 pts |
AI confidence
Needs refreshThe data refresh is due. Confidence will be reassessed against the refreshed history.
Model: State-space model, 167M (foundation model)
- Accuracy vs naive
- n/aNot evaluated
- Direction
- n/aNot evaluated
- Turning points
- n/aNot evaluated
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
Previous comparisonThe stored comparison uses earlier data or a previous model roster. An eligible nightly batch can compare both candidates, subject to call budgets and retry limits.
Models tested
State-space model, 167M scored lowest on the 6 older tests (1.02) and was chosen. The 6 recent tests played no part in the choice and give its grade (0.73). 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: Foundation model, Statistical, Machine learning, Neural network. Previous model roster.
| Model | Class and compute | Older tests | Recent tests | Role |
|---|---|---|---|---|
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
| State-space model, 167M (foundation model) | Foundation model · CPU | 1.02 | 0.73 | Serving |
| Agentic Investor TSFM (foundation model) | Foundation model · CPU | 1.13 | 0.72 | Tested |
| Exponential smoothing (statistical) | Statistical · CPU | 1.27 | 0.73 | Tested |
| Gradient-boosted trees (machine learning) | Machine learning · CPU | 1.38 | 0.92 | Tested |
| Hierarchical neural network (neural network) | Neural network · CPU | 2.81 | 0.71 | Tested |
Reading
That is the highest of the 120 readings since October 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| September 2026 | 103.5 pts |
| August 2026 | 103.3 pts |
| July 2026 | 102.7 pts |
| June 2026 | 102.9 pts |
| May 2026 | 102.8 pts |
| April 2026 | 102.0 pts |
| March 2026 | 102.4 pts |
| February 2026 | 101.9 pts |
| January 2026 | 101.3 pts |
| December 2025 | 101.8 pts |
| November 2025 | 101.6 pts |
| October 2025 | 101.3 pts |
| September 2025 | 101.3 pts |
| August 2025 | 101.0 pts |
| July 2025 | 100.5 pts |
| June 2025 | 100.9 pts |
| May 2025 | 101.0 pts |
| April 2025 | 100.3 pts |
| March 2025 | 100.6 pts |
| February 2025 | 100.7 pts |
| January 2025 | 99.9 pts |
| December 2024 | 100.7 pts |
| November 2024 | 100.4 pts |
| October 2024 | 100.1 pts |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Singapore Consumer Price Index in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators
Also stored for Singapore
- Singapore Average Weekly Hours
- Singapore Balance Of Trade
- Singapore Bank Lending Rate
- Singapore Bankruptcies
- Singapore Banks Balance Sheet
- Singapore Business Confidence Index
- Singapore CO2 Emissions
- Singapore CPI Housing Utilities
- Singapore CPI Transportation
- Singapore Capital Flows
- Singapore Car Registrations
- Singapore Central Bank Balance Sheet