Top ‘N’ Variant Random Forest Model for High Utility Itemsets Recommendation

Abstract

High-utility based itemset mining is the advancement of recurrent pattern mining that discovers occurrence of frequent transactions from a huge database. The issues in frequent pattern mining involve the elimination of quantities purchased by the customers and cost of purchased product. This can be resolved by high utility itemset mining which includes quantities and profit of the products in the transactions. The conventional association rule mining algorithms results in huge memory consumption due to the complexity in pruning the search space. In this paper, machine learning based high-utility itemset mining is applied to predict next order in an online grocery store depending on the transactions. The overall goal is to enhance the business profitability by stocking the high utility items in market. The Top ‘N’ variant Random Forest model is proposed to recommend the high utility itemsets, thereby predicting the reordered/next ordered items. The model is evaluated using Instacart market dataset to measure accuracy, precision and recall.

Keywords

• high utility itemset
• random forest
• machine learning
• association mining
• frequent itemsets
• feature selection