Paper_IJPE_Repository_1_Dataset_Purchases_Original_and_Augmented
收藏NIAID Data Ecosystem2026-05-02 收录
下载链接：
https://data.mendeley.com/datasets/24j2xp2xvy
下载链接
链接失效反馈官方服务：
资源简介：
This repository contains two datasets:
Original Dataset (100 rows) – A manufacturer-provided dataset of purchased items.
Augmented Dataset (10,000 rows) – A synthetically generated dataset designed for use in the FP-Growth algorithm to extract risk interdependency rules.
The augmentation process was performed using a Synthetic Data Generation technique based on Probabilistic Distribution, ensuring that newly generated categorical values align with the original data’s probability distribution. To maintain logical consistency, the algorithm leverages conditional probability distributions to preserve attribute relationships and dependencies. This approach guarantees realistic, coherent, and statistically valid synthetic data.
创建时间：
2025-02-24
