Moulds are common aeroallergens and Cladosporium is considered to be one of the more prevalent examples of these. Aiming to reduce the risk for allergic individuals, we constructed predictive models for the fungal spore circulation in Szczecin, Poland. Monthly forecasting models were developed for the airborne spore concentrations of Cladosporium, the most abundant fungal taxa in the area. Aerobiological sampling was conducted over 2004–2007, using a Lanzoni trap. Simultaneously, the following meteorological parameters were recorded: daily level of precipitation, maximum and average wind speed, relative humidity, maximum, minimum, average and dew point temperature. The original factors, as well as with lags (up to 3 days), were used as the explaining variables. Due to non‐linearity and non‐normality of the data set, Cladosporium spore concentrations were predicted using artificial neural networks (ANN). The final model included classification (spore presence or absence) and regression for spore seasons with log(x+1) transformed Cladosporium spore concentration. All variables, except average wind speed 3 days previously and precipitation (on the same day and with lags) were factors important in classification. In the regression model for spore seasons, close relationships were noted between Cladosporium spore concentration and dew point temperature the previous day, humidity, and minimum and maximum temperatures. Additionally, time series prediction was performed. Our study shows that ANN models are applicable to forecasting Cladosporium spore concentration with high accuracy.