Digital Decision Support for Refurbishment (2DSR)

Refurbishment represents a key industrial pathway in the emerging Circular Economy, however scaling up refurbishment in a way that is profitable requires firms to navigate complex decisions, slowing the transition to circular business models at the scale of individual firms, sectors, and society at-large.

This project is focused on data-driven development and secure exchange of data between process and actors. We will use machine learning to develop an image-based algorithm that supports refurbishment decisions by expediting estimations that traditionally require costly expert assessment and/or extensive resources. These estimations are enabled by data sharing among firms and organizations in the furniture value chain. Image-based estimations include (1) product classification; (2) the profit margin of refurbishment decisions; (3) relative circularity of a refurbishment decision as compared to purchasing a new product; and (4) relative environmental impact of a refurbishment decision as compared to purchasing a new product. Combined, these estimates will offer multicriteria decision support to firms while contributing to knowledge about the relationship between profitability, circularity, and climate impact. The project will also take advantage of collaboration within the furniture industry to develop scenarios that favor refurbishment instead of keeping underutilized furniture in storage or sending it to the landfill. Over time, as more industrial actors contribute data to the DSS, it will be able to support a broader range of circular decisions in the furniture industry and beyond.