The Good, the Bad and the Ugly: Workers Profiling Through Clustering Analysis

During the last five years, the sharing economy has emerged as one of the main business models to offer goods and services. Indeed, delivery and transportation are industries for which “sharing” has had one of the biggest impacts, with companies such as: Uber, Lyft or Cabify. However, like in any traditional company, human resource management is an issue for sharing economy firms. Our work aims to infer patterns regarding the performance of human resources in this context. We used unsupervised classification techniques over employee records from a delivery company that uses a sharing economy business model. We propose an automatic and scalable framework to discover efficient groups of workers, using features from logistic, geographical and temporal information. Although previous similar works have presented promising results, unlike them, we do not use demographic information about the employees. Our results suggest that deliveries per day, the kilometers covered by the worker and the companies that occupy a delivery agent are important features to determine outstanding workers. The framework proposed can turn into a key point to keep the exponential growth of these kind of companies during the time.