Data science has become increasingly relevant in the furniture industry to help companies overcome challenges such as the scarcity of raw materials and fierce competition in the globalized market. In addition, data analysis can also help companies better understand their customer profile and identify market trends. It can be applied to several management problems, such as sales analysis, cus- tomer behavior and targeted advertising. However, although Enterprise Resources Planning systems integrate knowledge and provide reporting tools for users to analyze data, supporting decision-making is not their primary purpose. This work presents a Data Science Trajectory (DST) model applied to commercial transac- tions in a case study of a real company in the furniture segment. It is intended to serve as a reference for data analysts who wish to incorporate this proce- dure into business routines based on commercial data. From the modeling of the DST implemented with machine learning techniques, we present differentiated results related to the discovery/understanding of the problems and proposition of interventions.
Read full abstract