Supply Chain Optimization in the Retail Industry by Integrating Apriori Algorithms and Time Series Forecasting in Business Intelligence

Abstract

This study investigates the integration of the Apriori algorithm and time series
forecasting within a Business Intelligence (BI) framework to optimize supply
chain operations in the retail industry. The Apriori algorithm was utilized to
identify significant purchasing patterns, enabling strategic decisions such as
product bundling and cross-selling. Concurrently, time series forecasting,
with an ARIMA model achieving a mean absolute percentage error (MAPE)
of 8%, provided accurate demand predictions, supporting improved inventory
management and resource allocation. The integration of these methods into a
BI dashboard facilitated real-time monitoring and data-driven decision
making, leading to enhanced operational efficiency and reduced costs. While
challenges such as data quality, computational resource demands, and user
adaptability were observed, this research underscores the transformative
potential of analytics in retail supply chain management. Future advancements
in machine learning and IoT integration are recommended to further enhance
system performance. Overall, this study demonstrates a pathway for retailers
to achieve operational excellence and superior customer satisfaction through
data-driven strategies.