My projects

 This article discusses an experiment that analyzed a dataset of 16,614 e-commerce web cookie records from a single website in order to identify which variables had the greatest impact on total transaction revenue. The data was cleaned and normalized, and a logistic regression model was used to predict the dependent variable (total revenue) based on various independent variables. The results showed that the model had an accuracy of 93.03%, specificity of 99.72%, and sensitivity of 1.75%.