DAX (^GDAXI) price forecast
DAX is trading at 25,464. Over the next 4 hours our simulation puts it between 25,292 and 25,668— that's the 10th-to-90th percentile of 20,000 modelled outcomes, so roughly four times in five it should land inside that band. The model puts the odds of finishing higher at 54%. These are probabilities, not predictions of certainty, and the backtest below shows exactly how often the model has been right.
Price history & forecast cone — 10th–90th percentile of 20,000 simulated futures
DAX forecast by timeframe
| Timeframe | Likely range | Midpoint | Odds higher |
|---|---|---|---|
| 5 Minutes | 25,431 – 25,500 | 25,465 | 52% |
| 15 Minutes | 25,408 – 25,528 | 25,468 | 54% |
| 1 Hour | 25,374 – 25,562 | 25,468 | 52% |
| 4 Hours | 25,292 – 25,668 | 25,479 | 54% |
| 30 Minutes | Available on Pro → | ||
| 1 Day | Available on Pro → | ||
| 1 Week | Available on Pro → | ||
| 1 Month | Available on Pro → | ||
| 6 Months | Available on Pro → | ||
| 1 Year | Available on Pro → | ||
| 5 Years | Available on Pro → | ||
Intraday horizons are free. Longer horizons — 1 day through 5 years — are part of Pro.
How accurate has this model been on DAX?
Every forecast site claims accuracy. Here is ours, measured by walk-forward backtest on data the model never saw during training. Where it has no edge over a naive baseline, we say so.
| Horizon | Directional accuracy | Baseline | Edge | Verdict |
|---|---|---|---|---|
| 1-day | 51.2% | 53.0% | -1.8% | no edge |
| 7-day | 57.4% | 57.1% | +0.2% | no edge |
| 30-day | 59.7% | 60.9% | -1.3% | no edge |
Backtested on 1820unseen samples. "No edge" means the model was no better than assuming the recent trend continues — an honest result, and a common one.
What the model is saying about DAX
The model projects modest gains for ^GDAXI from its current level near 25,464. Over one week it expects about 25,547 (+0.33%, prob_up 57.6%), with a p10–p90 range of roughly 24,763 to 26,359. The one-month view sees around 25,790 (+1.28%, prob_up 61.9%), and the one-year projection reaches about 29,879 (+17.34%, prob_up 82.3%). Confidence declines sharply with time: reliability is moderate at one week, low at one month and very low at one year. Annualised volatility of 17.18% and a trailing-month change of +2.02% frame these projections, and the widening ranges reflect that volatility compounding over longer horizons. Bluntly, the ML model shows no measurable edge: at 1, 7 and 30 days its accuracy (51.2%, 57.4%, 59.7%) fails to beat the naive baseline (53.0%, 57.1%, 60.9%) in every case. A shift in realised volatility, a break in recent momentum, or continued model underperformance versus baseline would undermine these projections, particularly the wide, very-low-reliability one-year estimate.
How to read this forecast
We don't publish a single price target, because nobody can know one. Instead the engine runs 20,000 simulated futures for DAX and reports the band containing the middle 80% of them — the 10th to 90th percentile. A wide band means genuine uncertainty; a narrow one means the recent range has been calm. The odds higher figure is a calibrated probability: when we say 60%, outcomes of that kind should finish higher about 60 times in 100. Near 50% there is no directional signal at all, and the range itself is the entire forecast.
More depth: what a forecast cone is, how to read a P10–P90 range, and what makes a probability trustworthy. Our public accuracy scorecard shows where the model has an edge — and where it has none.
See the live DAX forecast
Streaming prices, an interactive cone across every timeframe, and the full honesty scorecard.
Open DAX in Coneview →Other index forecasts
Forecasts are probabilistic estimates from historical price data, not financial advice. Short-horizon direction has only a small measurable edge; long-horizon numbers reflect drift plus widening uncertainty and should be read as ranges, not targets. Figures update hourly. Coneview provides statistical market information, not financial advice.