Exploring the Relationship Between Data Science and Circular Economy: an Enhanced CRISP-DM Process Model

Abstract

To date, data science and analytics have received much attention from organizations seeking to explore how to use their massive volumes of data to create value and accelerate the adoption of Circular Economy (CE) concepts. The correct utilization of analytics with circular strategies may enable a step change that goes beyond incremental efficiency gains towards a more sustainable and circular economy. However, the adoption of such smart circular strategies by the industry is lagging, and few studies have detailed how to operationalize this potential at scale. Motivated by this, this study seeks to address how organizations can better structure their data understanding and preparation to align with overall business and CE goals. Therefore, based on the literature and a case study the relationship between data science and the CE is explored, and a generic process model is proposed. The proposed process model extends the Cross Industry Standard Process for Data Mining (CRISP-DM) with an additional phase of data validation and integrates the concept of analytic profiles. We demonstrate its application for the case study of a manufacturing company seeking to implement the smart circular strategy - predictive maintenance.