skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices

Customer Segmentation in the Brazilian Free Energy Market by Machine Learning

Santos, Moises R. ; Mastelini, Saulo M. ; Paula, Marcos B.S. ; Guarnier, Ewerton ; Silva, Donato ; Santos, Maria E. C. M. ; Campos, Eduardo F. C. ; Picarelli, Lucas B.

2023 IEEE 7th Conference on Energy Internet and Energy System Integration (EI2), 2023, p.3276-3281

IEEE

Sem texto completo

Citações Citado por
  • Título:
    Customer Segmentation in the Brazilian Free Energy Market by Machine Learning
  • Autor: Santos, Moises R. ; Mastelini, Saulo M. ; Paula, Marcos B.S. ; Guarnier, Ewerton ; Silva, Donato ; Santos, Maria E. C. M. ; Campos, Eduardo F. C. ; Picarelli, Lucas B.
  • Assuntos: Clustering ; Clustering algorithms ; Consumption Profiles ; Customer Segmentation ; Industries ; Machine learning ; Performance evaluation ; Propulsion ; System integration ; Technological innovation
  • É parte de: 2023 IEEE 7th Conference on Energy Internet and Energy System Integration (EI2), 2023, p.3276-3281
  • Descrição: The Brazilian free energy market is currently ex-periencing a significant transformation, propelled by a series of deregulation initiatives that are expected to culminate by the decade's end. This research delves into the intricate landscape of hourly energy consumption patterns among customers in the free energy market, with the primary objective of unveiling distinct profiles associated with seasonality, flexibility, and modulation. The insights drawn from customer profiling analysis pave the way for the delivery of tailored, individualized solutions and the formulation of highly competitive offers. Our approach leveraged unsupervised machine learning techniques, specifically Density and Hierarchical-based clustering, to craft a robust model for the precise determination of customer profiles. A noteworthy aspect of our study lies in the development of clusters based on customers' industry sectors, serving as a baseline for performance evaluation when juxtaposed against our automated clustering strategy. This approach allowed for the extraction of meaningful and informative performance indicators from a practical application perspective. It is worth emphasizing that our proposed machine learning-based clustering algorithm outperformed activity-based grouping, demonstrating superior performance in its ability to discern and categorize customer segments effectively.
  • Editor: IEEE
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  5 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.