no code implementations • 1 Feb 2024 • Sahab Zandi, Kamesh Korangi, María Óskarsdóttir, Christophe Mues, Cristián Bravo
We enhance the model by using a custom attention mechanism that weights the different time snapshots according to their importance.
1 code implementation • 16 Jul 2023 • Elena Tiukhova, Emiliano Penaloza, María Óskarsdóttir, Bart Baesens, Monique Snoeck, Cristián Bravo
We compare the results of various models to demonstrate the importance of capturing graph representation, temporal dependencies, and using a profit-driven methodology for evaluation.
no code implementations • 27 Jun 2023 • Sherly Alfonso-Sánchez, Jesús Solano, Alejandro Correa-Bahnsen, Kristina P. Sendova, Cristián Bravo
Second, given the particularities of our problem, we used an offline learning strategy to simulate the impact of the action based on historical data from a super-app in Latin America to train our reinforcement learning agent.
1 code implementation • 21 Apr 2023 • Mahsa Tavakoli, Rohitash Chandra, Fengrui Tian, Cristián Bravo
In this paper, we present an analysis of the most effective architectures for the fusion of deep learning models for the prediction of company credit rating classes, by using structured and unstructured datasets of different types.
no code implementations • 31 Dec 2022 • Ricardo Muñoz-Cancino, Cristián Bravo, Sebastián A. Ríos, Manuel Graña
Credit scoring models are the primary instrument used by financial institutions to manage credit risk.
1 code implementation • 15 Nov 2022 • Elena Tiukhova, Emiliano Penaloza, María Óskarsdóttir, Hernan Garcia, Alejandro Correa Bahnsen, Bart Baesens, Monique Snoeck, Cristián Bravo
Leveraging network information for prediction tasks has become a common practice in many domains.
no code implementations • 13 Apr 2022 • Ricardo Muñoz-Cancino, Cristián Bravo, Sebastián A. Ríos, Manuel Graña
Application scoring is used to decide whether to grant a credit or not, while behavioral scoring is used mainly for portfolio management and to take preventive actions in case of default signals.
no code implementations • 2 Dec 2021 • Matthew Stevenson, Christophe Mues, Cristián Bravo
We consider the suitability of this data not just on its own but also as an auxiliary source of data in combination with demographic features, thus providing a realistic use case for the embeddings.
no code implementations • 26 Nov 2021 • Ricardo Muñoz-Cancino, Cristián Bravo, Sebastián A. Ríos, Manuel Graña
Here we introduce a framework to improve credit scoring models by blending several Graph Representation Learning methods: feature engineering, graph embeddings, and graph neural networks.
no code implementations • 18 Nov 2021 • Kamesh Korangi, Christophe Mues, Cristián Bravo
In this paper, we study mid-cap companies, i. e. publicly traded companies with less than US $10 billion in market capitalisation.
1 code implementation • 10 Dec 2020 • David Barrera Ferro, Sally Brailsford, Cristián Bravo, Honora Smith
In this context many researchers have used multiple regression models to identify patient and appointment characteristics than can be used as good predictors for no-show probabilities.
1 code implementation • 19 Oct 2020 • María Óskarsdóttir, Cristián Bravo
We present a multilayer network model for credit risk assessment.
1 code implementation • 25 May 2020 • Cristián Bravo, María Óskarsdóttir
Our personalized PageRank algorithm for multilayer networks allows for quantifying how credit risk evolves across time and propagates through these networks.
no code implementations • 9 May 2020 • Luisa Roa, Alejandro Correa-Bahnsen, Gabriel Suarez, Fernando Cortés-Tejada, María A. Luque, Cristián Bravo
In this paper we present the impact of alternative data that originates from an app-based marketplace, in contrast to traditional bureau data, upon credit scoring models.
no code implementations • 19 Mar 2020 • Matthew Stevenson, Christophe Mues, Cristián Bravo
Compared to consumer lending, Micro, Small and Medium Enterprise (mSME) credit risk modelling is particularly challenging, as, often, the same sources of information are not available.
no code implementations • 23 Feb 2020 • María Óskarsdóttir, Cristián Bravo, Carlos Sarraute, Jan Vanthienen, Bart Baesens
In terms of profit, the best model is the one built with only calling behavior features.