Now showing items 1-9 of 9

    • A human-in-the-loop approach based on explainability to improve NTL detection 

      Coma Puig, Bernat; Carmona Vargas, Josep (Institute of Electrical and Electronics Engineers (IEEE), 2021)
      Conference report
      Open Access
      Implementing systems based on Machine Learning to detect fraud and other Non-Technical Losses (NTL) is challenging: the data available is biased, and the algorithms currently used are black-boxes that cannot be either ...
    • A quality control method for fraud detection on utility customers without an active contract 

      Coma Puig, Bernat; Carmona Vargas, Josep (Association for Computing Machinery (ACM), 2018)
      Conference report
      Open Access
      Fraud detection in energy consumption has proven to be a difficult problem for current techniques. In general, the approaches used in this area are restricted to compute a fraud score for each client based on its behaviour. ...
    • Bridging the gap between energy consumption and distribution through non-technical loss detection 

      Coma Puig, Bernat; Carmona Vargas, Josep (2019-05-01)
      Article
      Open Access
      The application of Artificial Intelligence techniques in industry equips companies with new essential tools to improve their principal processes. This is especially true for energy companies, as they have the opportunity, ...
    • Collaborative Filtering Ensemble for Personalized Name Recommendation 

      Coma Puig, Bernat (Universitat Politècnica de Catalunya / Leibniz Universität Hannover, 2013)
      Master thesis (pre-Bologna period)
      Open Access
      Covenantee:   Leibniz Universität Hannover
      Out of thousands of names to choose from, picking the right one for your child is a daunting task. In this thesis, our objective is to help parents make an informed decision while choosing a name for their baby. To this ...
    • Explainable predictive process monitoring 

      Galanti, Riccardo; Coma Puig, Bernat; de Leoni, Massimiliano; Carmona Vargas, Josep; Navarin, Nicolò (Institute of Electrical and Electronics Engineers (IEEE), 2020)
      Conference report
      Open Access
      Predictive Business Process Monitoring is becoming an essential aid for organizations, providing online operational support of their processes. This paper tackles the fundamental problem of equipping predictive business ...
    • Fraud detection in energy consumption: a supervised approach 

      Coma Puig, Bernat; Carmona Vargas, Josep; Gavaldà Mestre, Ricard; Alcoverro, Santiago; Martín, Victor (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Conference lecture
      Open Access
      Data from utility meters (gas, electricity, water) is a rich source of information for distribution companies, beyond billing. In this paper we present a supervised technique, which primarily but not only feeds on meter ...
    • Human-aware application of data science techniques 

      Coma Puig, Bernat (Universitat Politècnica de Catalunya, 2022-03-02)
      Doctoral thesis
      Open Access
      In recent years there has been an increase in the use of artificial intelligence and other data-based techniques to automate decision-making in companies, and discover new knowledge in research. In many cases, all this has ...
    • Knowledge-based segmentation to improve accuracy and explainability in non-technical losses detection 

      Calvo Ibáñez, Albert; Coma Puig, Bernat; Carmona Vargas, Josep; Arias Vicente, Marta (2020-10-30)
      Article
      Open Access
      Utility companies have a great interest in identifying energy losses. Here, we focus on Non-Technical Losses (NTL), which refer to losses caused by utility theft or meter errors. Typically, utility companies resort to ...
    • Non-technical losses detection in energy consumption focusing on energy recovery and explainability 

      Coma Puig, Bernat; Carmona Vargas, Josep (2021-09-29)
      Article
      Open Access
      Non-technical losses (NTL) is a problem that many utility companies try to solve, often using black-box supervised classifcation algorithms. In general, this approach achieves good results. However, in practice, NTL detection ...