Reshaped and Reduced Dimensionality Reduction Data Technique on Association Rule Mining

Online shops implement market basket analysis, where its association rule analysis helps people with their online shopping. Association rule's performance depends on the quality of the dataset. The association rule analysis depends on two values, namely the support value and the confidence value. There are two novelty techniques for preparing the dataset, reshape dataset technique and reduce dataset technique. The reshape dataset technique will decrease the dataset dimension on the number of rows; meanwhile, the reduced dataset technique will decrease the dataset by implementing the IST- EFP algorithm. This research compares 30%, 40%, 50%, 55% reshaped datasets against the reduced dataset. Both datasets can prune the original dataset dimension using the same confidence values on the strict rules. This research will analyze both techniques' performance by comparing the support value and confidence value against the original dataset. Both methods can reduce the dimensions of the dataset without changing the confidence value with a difference of less than 0.1% in the support value obtained; the reduced dataset has a better result.