A Quarterly High RFM Mining Algorithm for Big Data Management.

In today's highly competitive retail industry, offline stores face increasing pressure on profitability. They hope to improve their ability in shelf management with the help of big data technology. For this, on-shelf availability is an essential indicator of shelf data management and closely relates to customer purchase behavior. RFM (recency, frequency, and monetary) pattern mining is a powerful tool to evaluate the value of customer behavior. However, the existing RFM pattern mining algorithms do not consider the quarterly nature of goods, resulting in unreasonable shelf availability and difficulty in profit-making. To solve this problem, we propose a quarterly RFM mining algorithm for On-shelf products named OS-RFM. Our algorithm mines the high recency, high frequency, and high monetary patterns and considers the period of the on-shelf goods in quarterly units. We conducted experiments using two real datasets for numerical and graphical analysis to prove the algorithm's effectiveness. Compared with the state-of-the-art RFM mining algorithm, our algorithm can identify more patterns and performs well in terms of precision, recall, and F1-score, with the recall rate nearing 100%. Also, the novel algorithm operates with significantly shorter running times and more stable memory usage than existing mining algorithms. Additionally, we analyze the sales trends of products in different quarters and seasonal variations. The analysis assists businesses in maintaining reasonable on-shelf availability and achieving greater profitability. [ABSTRACT FROM AUTHOR]