no code implementations • 10 May 2024 • Enrique Riveros, Carla Vairetti, Christian Wegmann, Santiago Truffa, Sebastián Maldonado
This paper aims to enrich the capabilities of existing deep learning-based automated valuation models through an efficient graph representation of peer dependencies, thus capturing intricate spatial relationships.
no code implementations • 10 Oct 2023 • Nuria Gómez-Vargas, Sebastián Maldonado, Carla Vairetti
In this paper, we introduce a novel predict-and-optimize method for profit-driven churn prevention.
no code implementations • 9 Oct 2023 • Carla Vairetti, José Luis Assadi, Sebastián Maldonado
Imbalanced classification is a well-known challenge faced by many real-world applications.
no code implementations • 30 May 2023 • Sebastián Maldonado, Carla Vairetti, Katherine Jara, Miguel Carrasco, Julio López
In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks.
no code implementations • 24 Jul 2020 • Wouter Verbeke, Diego Olaya, Jeroen Berrevoets, Sam Verboven, Sebastián Maldonado
The framework is shown to instantiate to application-specific cost-sensitive performance measures that have been recently proposed for evaluating customer retention and response uplift models, and allows to maximize profitability when adopting a causal classification model for optimizing decision-making.