Machine Learning Algorithms for Pricing End-of-Life Remanufactured Laptops

Abstract

Due to the growing volume of e-waste in the world and its environmental impact, it is important to understand how to extend the useful life of electronic items. In this paper, we examine the remanufacturing process of end-of-life laptops for third-party remanufacturers and consider their pricing problem, which involves issues like a lack of reliable datasets, fluctuating costs of new components, and difficulties in benchmarking laptop prices, to name a few. We develop a unique approach that uses machine learning algorithms to help price remanufactured laptops. Our methodology involves a variety of techniques, which include an additive model, CART analysis, Random Forest, and Polynomial Regression. We consider depreciation and discount factors to account for the varying ages and conditions of laptops when estimating remanufactured laptop prices. Finally, we also compare our estimated prices to traditional prices. In summary, we leverage data-driven decision-making and develop a robust methodology for pricing remanufactured laptops to extend their lifespan.