From redundant association rules to product networks: A scalable confidence-improvement pruning and Maximum Spanning Tree approach

Vladimir Đurišić, Saša Vujošević, Ljiljana Kašćelan, Sunčica Vuković · 2026

Read From redundant association rules to product networks: A scalable confidence-improvement pruning and Maximum Spanning Tree approach by Vladimir Đurišić, Saša Vujošević, Ljiljana Kašćelan, Sunčica Vuković (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0356990.txt.

Description

Vladimir Đurišić and colleagues confronted a familiar retail analytics problem: software that mines shopping baskets for product pairings returns hundreds of thousands of rules, most of them redundant. Their 2026 study built a pruning method that keeps only rules adding real confidence, then turned the survivors into a product network and extracted its strongest backbone.

On a Montenegrin retail dataset of millions of baskets, the method cut rule counts by well over half while keeping the meaningful links. The backbone crowned delicatessen goods as the network's hub, with chains running into beauty products, fresh meat, and healthy produce. Retailers get a short, readable map for designing bundles, promotions, and shelf layouts instead of an unreadable rule dump.

Catalog record

CREATORVladimir Đurišić, Saša Vujošević, Ljiljana Kašćelan, Sunčica Vuković
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE80344
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0356990

Browse the full library · About the Tower of Babel