A prediction method of purchasing intention of e-commerce consumers in network marketing

In order to improve the accuracy of prediction results, a prediction method of purchasing intention of e-commerce consumers in network marketing is proposed. Firstly, collect consumer related data, standardise and handle outliers to eliminate dimensional differences between data. Secondly, a logistic regression algorithm is used to extract and select consumer features related to purchase intention, revealing consumers' purchasing preferences. Finally, based on the feature extraction results, a random forest algorithm is used to predict purchase intention. Gini impurity and information gain are used as splitting criteria to construct multiple decision trees, and the prediction results of all decision trees are synthesised by voting or averaging to obtain the final prediction result. The experimental results show that the root mean square error of the proposed method is relatively low, with the highest normalised information value reaching 0.89, indicating that it can accurately reflect consumers' purchasing intention.