How to read the dashboard

What the model predicts

The model does not claim to name tomorrow's exact exchange rate — for a freely floating currency that is not possible, and anyone who promises a single precise number is guessing. Instead it forecasts a corridor: the range the USD/PLN rate is likely to stay within, day by day into the future.

That corridor is built from two kinds of reasoning working together:

• Macroeconomic drivers — interest-rate differentials between the Fed and the National Bank of Poland (carry), scheduled events (rate decisions, inflation and jobs data), and the balance of market-moving news. These shape where the risks lean.
• Statistical laws — how much the rate has actually been moving lately (realised volatility) and the fact that, over short horizons, an exchange rate behaves much like a random walk. These set how wide the corridor has to be to stay honest, and it widens the further out you look because uncertainty compounds with time.

The central line is an axis, not a promise. It runs through the middle of the corridor and shows the balance of risks — which way the pressures lean and how strongly. When the line slopes up, the upside risks outweigh the downside; when it slopes down, the reverse. Read the band as the forecast and the line as its centre of gravity, not as a precise price target.

Chart lines

• Actual (green) — the real USD/PLN exchange rate published by the National Bank of Poland (NBP). This is the ground truth.
• Past predictions (dark blue) — forecasts the model made in the past. You can compare them against the green line to see how accurate the model was.
• Forecast (light blue) — the model's current outlook for the coming days. The shaded band is the actual forecast: the corridor the rate is expected to stay within. The line running through it is the corridor's axis (its midpoint) — a centre of gravity showing which way the risks lean, not an exact price. The whole thing fades as it extends further into the future, reflecting the corridor widening as uncertainty grows.

Where the points sit within a day

Each point on every line is placed at the time of day the forecast cycle finished, not at midnight. The completion time is rounded to the nearest half hour (e.g. a run that finished at 13:04 lands at 13:00, one at 13:28 lands at 13:30). So the whole picture sits at "when the forecast was produced" for each day, and the date labels along the bottom are centered on midday of the day they describe.

Red shaded segments — wrong trend direction

Line segments shaded in red are where the forecast got the trend direction wrong. The model predicted the rate would move one way, but the NBP fixing moved the opposite way — it called USD up while the rate fell, or called USD down while the rate rose.

This is purely about direction, not about how big the miss was: a red segment means the forecast pointed the wrong way. This includes the case where the model predicted a clear move but the rate stayed flat — a trend that simply didn't happen counts as a direction miss. The shading covers only the final sloped leg into the mispredicted point, so it hugs the segment where the rate actually moved and never bleeds across flat carried-forward weekend or holiday days.

Segments with no shading are where the model called the direction correctly, or where there was no direction to judge at all — the rate didn't change (e.g. a carried-forward non-publish day) or the forecast itself was flat.

Vertical lines

• Yellow line — marks the date of the last prediction cycle. Everything to the left is history; everything to the right is the current forecast.
• White line — today's date. Only visible when today differs from the last cycle date, so you can see how much time has passed since the forecast was generated.

Event markers

• Green vertical bar — a macroeconomic or political event that the model expects to push USD up (or PLN down) on that date.
• Red vertical bar — an event expected to push USD down (or PLN up).

Each marker sits at midday of its date. Hover over any event marker to see a tooltip with the event name, expected impact, and confidence level.

Trend strips

At the bottom of the chart, colored horizontal strips show the predicted trend direction for each future time segment. Green means upward, red means downward, gray means flat. Hover for details including the driver, expected change, and confidence.

Weekday markers

A thin strip along the bottom of the chart labels each working day (Mon–Fri) across the whole timeline, past and future, centered on midday. Weekends are left blank. Past days carry a faint frame to match the look of the future trend strips; only the future strips are interactive (hover for trend details) — the past weekday frames are purely a visual guide.

Chart controls

• Mouse wheel — zoom in and out on the time axis.
• Click and drag — pan left and right through time.
• Double-click — reset zoom to the default 60-day view.

Accuracy metric (MAE)

The number displayed above the chart (e.g. MAE 0.0312 PLN) is the Mean Absolute Error — the average difference between the model's past predictions and the actual rate, measured in PLN. Lower is better. Use the horizon selector to see accuracy at different forecast distances (1, 7, or 14 days).

News section

Below the chart, the 10 most influential news stories are displayed. These are the articles and events that had the greatest impact on the model's current forecast.

News rating number

Each news tile shows a number in the top-right corner. This is the weight — how strongly this particular piece of news influenced the forecast, on a relative scale.

• Green number — the news pushes the forecast upward (USD strengthening / PLN weakening).
• Red number — the news pushes the forecast downward (USD weakening / PLN strengthening).
• Gray number — neutral or negligible impact.

News tiles are ranked by absolute weight: the first tile is the single most influential piece of news, regardless of direction. Click any tile to read the full article.