Výsledky vyhledávání - "Solano, Jesús"

Report

Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learning

Autor: Alfonso-Sánchez, Sherly, Solano, Jesús, Correa-Bahnsen, Alejandro, Sendova, Kristina P., Bravo, Cristián

Publikováno v: Alfonso-Sanchez, S., Solano, J., Correa-Bahnsen, A., Sendova, K. P., & Bravo, C. (2024). Optimizing credit limit adjustments under adversarial goals using reinforcement learning. European Journal of Operational Research 315(2): 802-817

Reinforcement learning has been explored for many problems, from video games with deterministic environments to portfolio and operations management in which scenarios are stochastic; however, there have been few attempts to test these methods in bank

Externí odkaz: http://arxiv.org/abs/2306.15585

Zobrazit plný text záznamu

Report

SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations

Autor: Solano, Jesus, Sanni, Mardhiyah, Camburu, Oana-Maria, Minervini, Pasquale

Publikováno v: ACL 2024

Models that generate natural language explanations (NLEs) for their predictions have recently gained increasing interest. However, this approach usually demands large datasets of human-written NLEs for the ground-truth answers at training time, which

Externí odkaz: http://arxiv.org/abs/2305.13235

Zobrazit plný text záznamu

Report

Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings

Autor: Quintero-Ossa, Ana María, Solano, Jesús, Jarcía, Hernán, Zarruk, David, Bahnsen, Alejandro Correa, Valencia, Carlos

Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organiza

Externí odkaz: http://arxiv.org/abs/2211.05717

Zobrazit plný text záznamu

Report

Proactive Detractor Detection Framework Based on Message-Wise Sentiment Analysis Over Customer Support Interactions

Autor: Gallo, Juan Sebastián Salcedo, Solano, Jesús, García, Javier Hernán, Zarruk-Valencia, David, Correa-Bahnsen, Alejandro

In this work, we propose a framework relying solely on chat-based customer support (CS) interactions for predicting the recommendation decision of individual users. For our case study, we analyzed a total number of 16.4k users and 48.7k customer supp

Externí odkaz: http://arxiv.org/abs/2211.03923

Zobrazit plný text záznamu

Report

Feature-Level Fusion of Super-App and Telecommunication Alternative Data Sources for Credit Card Fraud Detection

Autor: Acevedo-Viloria, Jaime D., Pérez, Sebastián Soriano, Solano, Jesus, Zarruk-Valencia, David, Paulin, Fernando G., Correa-Bahnsen, Alejandro

Identity theft is a major problem for credit lenders when there's not enough data to corroborate a customer's identity. Among super-apps large digital platforms that encompass many different services this problem is even more relevant; losing a clien

Externí odkaz: http://arxiv.org/abs/2111.03707

Zobrazit plný text záznamu

Report

FooBaR: Fault Fooling Backdoor Attack on Neural Network Training

Autor: Breier, Jakub, Hou, Xiaolu, Ochoa, Martín, Solano, Jesus

Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase with the intention to cause a misclassification. In this work

Externí odkaz: http://arxiv.org/abs/2109.11249

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání