Promoting a novel method for warranty claim prediction based on social network data

Sajjad Shokouhyar, Sadra Ahmadi and Mahdi Ashrafzadeh

Reliability Engineering and System Safety, 2021, vol. 216, issue C

Abstract: Warranty plays an important role in retaining consumers' loyalty, increasing the competitive advantage and the profit of companies. Moreover, warranty claim prediction based on social media is a novel area, enabling managers to foresee problems in production and take the proper measures to mitigate them. The higher the precision of the warranty claim predictions, the lower the risk the company faces. This paper examines the impacts of utilizing social media data on daily warranty claim prediction. In this paper, we showed that social media data could enhance the accuracy of daily warranty claim predictions. We cooperated with Sam Service Warranty Company that provides warranty and aftersales services for Samsung products in Iran. Warranty operational data along with Twitter data analyses were used to improve the precision of warranty claim prediction. Operational data from Sam Service Company include the total number of warranties, the number of warranties for new customers, and the number of warranties for those who return. A novel framework was presented that uses the Random Forrest algorithm for prediction of the number of daily warranty claims. The results show that our framework improves the accuracy of out-of-sample warranty claims predictions, with respective development at a range of 14.98% to 21.90% across various timeframes. Improving prediction accuracy enables managers to effectively minimize warranty-related costs, inventory levels, waste, and customer dissatisfaction while maximizing the return on investment, profit, efficiency, and customer satisfaction.

Keywords: Warranty claim prediction; Social media analysis; Random Forest method (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832021005196
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:216:y:2021:i:c:s0951832021005196

DOI: 10.1016/j.ress.2021.108010

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().