Serbia Balance Of Trade

Serbia · Monthly series · EC-RS-BOT

Latest, July 2026

-1.14B USD

+50.3M USD from June 2026

Open interactive chartSerbia Balance Of Trade in the app

-273.4M-1.069B-1.865BAugust 2016July 2027
History through July 2026, the forecast path to July 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for July 2027: -996.9M USD, with an 80% interval of -1.59B USD to -523.9M USD.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
August 2026-1.10B USD-1.24B USD-960.3M USD
September 2026-1.05B USD-1.28B USD-841.6M USD
October 2026-1.20B USD-1.52B USD-892.2M USD
November 2026-1.08B USD-1.37B USD-833.4M USD
December 2026-1.39B USD-1.76B USD-1.02B USD
January 2027-928.9M USD-1.51B USD-475.3M USD
February 2027-1.08B USD-1.31B USD-876.2M USD
March 2027-1.13B USD-1.47B USD-815.5M USD
April 2027-1.06B USD-1.71B USD-496.4M USD
May 2027-1.08B USD-1.87B USD-419.8M USD
June 2027-960.4M USD-1.72B USD-387.0M USD
July 2027-996.9M USD-1.59B USD-523.9M USD

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

AI confidence

Supported evidence

The point forecast beat the no-change baseline overall and in a majority of the evaluated tests.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
+15%Beats the no-change baseline over 12 tests (12 tests, 8 won)
Direction
63%No clear edge over a coin flip (91 of 144 calls right in 12 tests)
Turning points
79 of 90Anticipated most turns (90 turns in 12 tests, 0 without a turn)
Error vs baseline
15% lowerError ratio 0.85; 1.00 is a tie.
Tests won
8 / 12Complete rolling backtests; ties count as no win.
Test period
2014-08-01 to 2026-07-0112 observations ahead per test.
80% band coverage
81%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 10% of the 119 earlier readings since August 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
July 2026-1.14B USD
June 2026-1.19B USD
May 2026-1.28B USD
April 2026-1.24B USD
March 2026-1.24B USD
February 2026-1.34B USD
January 2026-886.4M USD
December 2025-1.20B USD
November 2025-865.3M USD
October 2025-753.9M USD
September 2025-698.9M USD
August 2025-820.9M USD
July 2025-847.8M USD
June 2025-520.7M USD
May 2025-801.6M USD
April 2025-1.11B USD
March 2025-964.6M USD
February 2025-784.7M USD
January 2025-500.9M USD
December 2024-1.34B USD
November 2024-912.7M USD
October 2024-1.02B USD
September 2024-881.1M USD
August 2024-936.9M USD

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Serbia