The data is fed into the model, which simulates thousands of outcomes. Those possible outcomes create a band of probability for each party.
The upper and lower estimates for projected seats mean Labour and National could be deadlocked on the same number of seats.
The update, created after the release of last night's poll, forecasts six seats for the Greens, although the lower estimate remains zero seats.
The most probable path to forming a government remains, for both major parties, an alliance with New Zealand First, who are projected to win nine seats.
Before last night, he previous update to our model was based on the Newshub Reid Research poll release last Thursday. That had National almost 10 percentage points ahead - 47.3 per cent to 37.8 per cent.
The result was that our model projected National to win 54 seats, Labour 53.
To form a government, a party or coalition needs at least 61 out of 120 seats, or to reach a confidence-and-supply agreement.
The forecast model also includes predictions for candidates by every electorate. These are based on previous election results and take into account any polling that has taken place for a particular electorate.
There is different methodology for Epsom, which is unlike most other electorates because of tactical voting.
The visualisation also includes candidate and party vote predictions for Maori electorates. However, this is perhaps the hardest part of forecasting because of tactical voting and lack of consistent polling at electorate level.
We'll continue to update the Herald Forecast as new polls are released. It's becoming more responsive to the polls as we get nearer to the election on September 23.