Probabilistic coin forecast
What it shows
The QWave forecast for this coin: 10,000 simulated price paths built from hourly history and similar market setups. The card shows P(up), the median, the 80% interval, the band fan on the chart and how the model has done for this coin so far.
How to read it
Start with the P10-P90 band and its width, then check interval coverage with N: if it stays around 80%, the band can be trusted as a measure of uncertainty. Read P(up) carefully, because over short horizons it usually sits close to 50%.
Parameters
- Horizon (1 day, 7 days, 30 days)
- How far ahead the forecast reaches. Each horizon has its own forecast, settlement date and statistics, so 1 day and 30 days can look different without contradiction.
- P(up)
- The share of simulated paths that end the horizon above today's price. 50% is a coin flip; over a few days the value almost always sits near 50%, and that is the honest answer, not a fault.
- Neutral reading: From 45% to 55%: the model sees no edge on either side.
- Median (P50)
- The middle price from the simulation: half of the paths end lower, half higher. A median close to today's price is a normal result.
- 80% forecast interval (P10-P90)
- The price band at the end of the horizon: in 80 cases out of 100 the price should land inside, 10 fall below and 10 above. A wide band means high uncertainty. This is the most important number on the card.
- Fan chart
- Price history on the left, the NOW point is when the forecast was computed, and the bands fan out to the right: the lightest P05-P95 (90% of paths), the middle P10-P90 (80%), the darkest P25-P75 (half). The dashed line is the median. Price that arrived after the forecast is drawn over the bands.
- Direction hit rate (N)
- How often the side indicated by P(up) matched the real price change. N is the number of settled forecasts. Below the minimum sample we write “too little data” instead of a percentage.
- Negative reading: A result around 50% is normal for direction over a few days. The model is judged mainly by interval coverage.
- 80% interval coverage (N)
- How often the real price actually landed inside the P10-P90 band. An honest model scores about 80% here: clearly less means the band is too narrow, clearly more that it is too wide.
- Positive reading: From 75% to 85%: the band tells the truth about uncertainty.
- Historical test or live results
- Until there are enough settled live forecasts, the statistics come from the historical test: forecasts for past days computed only from data available before each day. The two sources are never mixed, and the label always says which one you see.
- Chance of a 10% move
- The share of paths that end the horizon at least 10% lower or at least 10% higher. It shows the scale of possible moves, not the direction.
- Volatility
- Current volatility against the last 90 days: low, normal, high or extreme. In high and extreme regimes the band is wider and reliability lower.
- Forecast reliability
- A 0-100 rating of the forecast's own quality: sample size, how well coverage and calibration held, data completeness and the volatility level. It is not the probability of a rise.
- Settlement
- A new forecast is made once a day (00:00 UTC) and frozen. After the due date an automated job takes the candle close at settlement time and records whether the direction matched and whether the price fell inside the intervals. Misses count exactly like hits.
Example
For 7 days the card shows: P(up) 48%, median -0.3%, 80% interval from 61,200 to 68,400 USD, 80% interval coverage: 79% (N=520), historical test. Read it as: the model sees no directional edge, but in the past a band this wide caught the price in 4 cases out of 5.