The value of customer behavior in supply chain management

  • This dissertation investigates the value of customer behavior in supply chain management through the application of (big) data analytics in demand forecasting. The use of advanced analytics in supply chain management is not novel. However, the growing expansion of data volumes provides companies with new opportunities to optimize their supply chain. Despite the rising interest from both academia and practice and the recent increase in publications in this area, empirical insights are still limited. At the same time, changes in customer expectations towards instant product delivery require companies to rethink their supply chain, where accurate demand forecasts are often at the core of enabling efficient and flexible processes. This makes the development of demand prediction models that can be used in practice especially relevant. We1 analyze the use of customer behavior in demand forecasting in three separate research papers. Leveraging data from research partners in the online fashion and construction industry, we assess the potential of the developed prediction models in three areas of application in supply chain management, namely order fulfillment, order picking, and inventory planning. In the first paper, we develop a prediction model for anticipatory shipping in the fashion industry, which predicts customers’ online purchases with the aim of shipping products in advance, and subsequently minimizing delivery times. Using various forecasting methods and data on customers’ behavior on the website, we test if, and how early, it is possible to predict online purchases. Results indicate that customer purchases are, to a certain extent, predictable, but anticipatory shipping comes at a high cost due to wrongly sent products. The second paper assesses the extent to which clickstream data can improve forecast accuracy for fashion products. Specifically, we assess which clickstream variables are most suitable for predicting demand, and identify the products that benefit most from this. Results indicate that clickstream data is especially useful for forecasting medium- and certain intermittent-demand products. A simulation of order picking for these products shows that using clickstream data in the forecast substantially decreases picking times. The third paper investigates how sequential pattern mining can be used to determine products with correlated demand, and how to leverage this as an input into forecasting for a supplier in the construction industry. We find that sequential pattern mining may be beneficial when used in combination with traditional forecasting methods, and that support vector regression models seem especially suited to forecast intermittent-demand products. An application to inventory planning shows that our developed forecasting model might reduce the company’s costs of inventory holding and lost sales by up to 6.9%. Overall, our research highlights the value of using customer behavior to enhance demand forecasting and the benefit of using improved forecasts in various applications in supply chain management. 1Referring to the authors of the respective chapters as noted at the beginning of each chapter.

Download full text files

Export metadata

Additional Services

Search Google Scholar Statistics
Metadaten
Author:Jennifer Weingarten
URN:urn:nbn:de:hbz:992-opus4-8889
Subtitle (English):predictive analytics applications in demand forecasting
Publisher:WHU
Place of publication:Vallendar
Referee:Stefan Spinler, Christian Schlereth
Document Type:Doctoral Thesis
Language:English
Date of Publication (online):2021/11/30
Date of first Publication:2021/11/30
Publishing Institution:WHU - Otto Beisheim School of Management
Granting Institution:WHU - Otto Beisheim School of Management
Date of final exam:2021/03/25
Release Date:2021/11/30
Tag:Nachfrageverhalten; Verbraucherverhalten
Consumer behavior; Supply Chain Management
Page Number:120
Institutes:WHU Supply Chain Management Group / Kühne Foundation Endowed Chair of Logistics Management
Licence (German):Copyright this PhD thesis