DAC05Group4_​DecisionTree

DAC05 Group 4 - Decision Tree Model

Data preparation was carried out using a sequence of preprocessing nodes in KNIME. Missing values were imputed, irrelevant variables were removed, outliers were treated using the IQR method, and the target variable was converted into a categorical format. These steps improved data quality and ensured that the dataset was suitable for building accurate and reliable predictive models.

The Numeric Outliers node was used to identify and treat extreme values in numerical variables using the Interquartile Range (IQR) method. Outliers were replaced with the closest permitted value to reduce their impact while retaining all observations in the dataset.

what's success factor for decision tree?