Abstract
The detection of purchasing behaviour of consumer customers belongs to the classical machine learning binary classification problem, which requires the use of a new dataset after downsampling to build a machine learning model and the selection of parameters for the visual display of the model.In this paper, we first performed data cleaning and pre-processing of the data, explored the complexity, non-linearity and other properties of the original data, performed logarithmic transformation and normalisation of the data pre-processing, and then selected the data features, established multiple machine learning models for modelling, adjusted the parameters using cross-validation and grid tuning, further optimised the models, calculated the evaluation metrics of the models, and compared the models, and finally used cross-validation and grid tuning to adjust parameters, further optimise the models, and calculate evaluation metrics of the models. The models were compared and finally the selected models were integrated using the Stacking method. Then the probability calibration was performed and the models were interpreted using SHAP values and PDP plots. This paper also adopts a rich visualisation approach for data and model presentation during data processing and modelling.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.