Singapore Banks Balance Sheet
Singapore · Monthly series · EC-SG-BBS
Latest, September 2026
4.15T SGD
+2.0% from August 2026
Forecast
Forecast for September 2027: 4.56T SGD, with an 80% interval of 3.54T SGD to 5.59T SGD.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| October 2026 | 4.14T SGD | 2.82T SGD | 5.45T SGD |
| November 2026 | 4.19T SGD | 3.00T SGD | 5.37T SGD |
| December 2026 | 4.22T SGD | 2.08T SGD | 6.37T SGD |
| January 2027 | 4.42T SGD | 2.99T SGD | 5.85T SGD |
| February 2027 | 4.40T SGD | 3.11T SGD | 5.69T SGD |
| March 2027 | 4.45T SGD | 2.79T SGD | 6.12T SGD |
| April 2027 | 4.49T SGD | 2.72T SGD | 6.26T SGD |
| May 2027 | 4.52T SGD | 2.61T SGD | 6.43T SGD |
| June 2027 | 4.53T SGD | 2.60T SGD | 6.47T SGD |
| July 2027 | 4.55T SGD | 3.38T SGD | 5.72T SGD |
| August 2027 | 4.56T SGD | 3.67T SGD | 5.45T SGD |
| September 2027 | 4.56T SGD | 3.54T SGD | 5.59T SGD |
AI confidence
Needs refreshThe data refresh is due. Confidence will be reassessed against the refreshed history.
Model: Gradient-boosted trees (machine learning)
- 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
Gradient-boosted trees scored lowest on the 6 older tests (0.63) and was chosen. The 6 recent tests played no part in the choice and give its grade (1.55). 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, Statistical, Neural network, Foundation model. Previous model roster.
| Model | Class and compute | Older tests | Recent tests | Role |
|---|---|---|---|---|
| Gradient-boosted trees (machine learning) | Machine learning · CPU | 0.63 | 1.55 | Serving |
| Exponential smoothing (statistical) | Statistical · CPU | 0.64 | 0.88 | Tested |
| Hierarchical neural network (neural network) | Neural network · CPU | 0.67 | 12.33 | Tested |
| State-space model, 167M (foundation model) | Foundation model · CPU | 0.67 | 1.11 | Tested |
| Agentic Investor TSFM (foundation model) | Foundation model · CPU | 0.67 | 0.92 | Tested |
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
Reading
That is the highest of the 120 readings since October 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| September 2026 | 4.15T SGD |
| August 2026 | 4.07T SGD |
| July 2026 | 4.05T SGD |
| June 2026 | 4.11T SGD |
| May 2026 | 4.02T SGD |
| April 2026 | 4.00T SGD |
| March 2026 | 4.07T SGD |
| February 2026 | 3.84T SGD |
| January 2026 | 3.85T SGD |
| December 2025 | 3.87T SGD |
| November 2025 | 3.79T SGD |
| October 2025 | 3.75T SGD |
| September 2025 | 3.73T SGD |
| August 2025 | 3.65T SGD |
| July 2025 | 3.69T SGD |
| June 2025 | 3.63T SGD |
| May 2025 | 3.61T SGD |
| April 2025 | 3.65T SGD |
| March 2025 | 3.63T SGD |
| February 2025 | 3.61T SGD |
| January 2025 | 3.67T SGD |
| December 2024 | 3.74T SGD |
| November 2024 | 3.55T SGD |
| October 2024 | 3.56T SGD |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Singapore Banks Balance Sheet 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 Business Confidence Index
- Singapore CO2 Emissions
- Singapore CPI Housing Utilities
- Singapore CPI Transportation
- Singapore Capital Flows
- Singapore Car Registrations
- Singapore Central Bank Balance Sheet
- Singapore Changes In Inventories