Demand Forecasting of Retail Sales Using Data Analytics and Statistical Programming

• Main Authors: Lalou Panagiota, Ponis Stavros T., Efthymiou Orestis K.
• Format: Article
• Language: English
• Published: Sciendo 2020-06-01
• Series: Management şi Marketing
• Subjects: demand forecasting; decision making; data analytics; statistical programming; retail sales; third party logistics (3pl) operators
• Online Access: https://doi.org/10.2478/mmcks-2020-0012

Forecasting the demand of network of retail sales is a rather challenging task, especially nowadays where integration of online and physical store orders creates an abundance of data that has to be efficiently stored, analyzed, understood and finally, become ready to be acted upon in a very short time frame. The challenge becomes even bigger for added-value third party logistics (3PL) operators, since in most cases and demand forecasting aside, they are also responsible for receiving, storing and breaking inbound quantities from suppliers, consolidating and picking retail orders and finally plan and organize shipments on a daily basis. This paper argues that data analytics can play a critical role in contemporary logistics and especially in demand data management and forecasting of retail distribution networks. The main objective of the research presented in this paper is to showcase how data analytics can support the 3PL decision making process on replenishing the network stores, thus improving inventory management in both Distribution Centre (DC) and retail outlet levels and the workload planning of human resources and DC automations. To do so, this paper presents the case of a Greek 3PL provider fulfilling physical store and online orders on behalf of a large sporting goods importer operating a network of 129 stores in five different countries. The authors utilize the power of ‘R’, a statistical programming language, which is well-equipped with a multitude of libraries for this purpose, to compare demand forecasting methods and identify the one producing the smallest forecast error.