Javier Arroyo

Javier Arroyo

Auto-generated profile, based on publicly available information

Javier Arroyo

Dept. of Computer Science, Universidad de Alcalá, Madrid, Spain and Institute of Knowledge Technology, Universidad Complutense de Madrid, Madrid, Spain

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2020 in IEEE Access
Verified
Journal Article
Open access
MAMiller Janny Ariza-Garzon
Miller Janny Ariza-Garzon
JAJavier Arroyo
Javier Arroyo
ACAntonio Caparrini
Antonio Caparrini
MSMaría Jesús Segovia-Vargas
María Jesús Segovia-Vargas
Peer-to-peer (P2P) lending demands effective and explainable credit risk models. Typical machine learning algorithms offer high prediction performance, but most of them lack explanatory power. However, this deficiency can be solved with the help of the explainability tools proposed in the last few years, such as the SHAP values. In this work, we assess the well-known logistic regression model and several machine learning algorithms for granting scoring in P2P lending. The comparison reveals that the machine learning alternative is superior in terms of not only classification performance but also explainability. More precisely, the SHAP values reveal that machine learning algorithms can reflect dispersion, nonlinearity and structural breaks in the relationships between each feature and the target variable. Our results demonstrate that is possible to have machine learning credit scoring models be both accurate and transparent. Such models provide the trust that the industry, regulators and end-users demand in P2P lending and may lead to a wider adoption of machine learning in this and other risk assessment applications where explainability is required.

1 October 2021 in Journal of Internet Services and Applications
Verified
Journal Article
Open access
PDF file
YFYoussef Faqir-Rhazoui
Youssef Faqir-Rhazoui
JAJavier Arroyo
Javier Arroyo
SHSamer Hassan
Samer Hassan
Blockchain technology has enabled a new kind of distributed systems. Beyond its early applications in Finance, it has also allowed the emergence of novel new ways of governance and coordination. The most relevant of these are the so-called Decentralized Autonomous Organizations (DAOs). DAOs typically implement decision-making systems to make it possible for their online community to reach agreements. As a result of these agreements, the DAO operates automatically by executing the appropriate portion of code on the blockchain network (e.g., hire people, delivers payments, invests in financial products, etc). In the last few years, several platforms such as Aragon, DAOstack and DAOhaus, have emerged to facilitate the creation of DAOs. As a result, hundreds of these new organizations have appeared, with their communities interacting mediated by blockchain. However, the literature has yet to appropriately explore empirically this phenomena. In this paper, we aim to shed light on the current state of the DAO ecosystem. We review the three main platforms nowadays (Aragon, DAOstack, DAOhaus) which facilitate the creation and management of DAOs. Thus, we introduce their main differences, and compare them using quantitative metrics. For such comparison, we retrieve data from both the main Ethereum network (mainnet) and a parallel Ethereum network (xDai). We analyze data from 72,320 users and 2,353 DAO communities in order to study the three ecosystems across four dimensions: growth, activity, voting system and funds. Our results show that there are notable differences among the DAO platforms in terms of growth and activity, and also in terms of voting results. Still, we consider that our work is only a first step and that further research is needed to better understand these communities, and evaluate their level of accomplishment in reaching decentralized governance.

30 August 2019 in IEEE Access
Verified
Journal Article
Open access
JAJavier Arroyo
Javier Arroyo
FCFrancesco Corea
Francesco Corea
GJGuillermo Jimenez-Diaz
Guillermo Jimenez-Diaz
JRJuan Recio-Garcia
Juan Recio-Garcia
The venture capital (VC) industry offers opportunities for investment in early-stage companies where uncertainty is very high. Unfortunately, the tools investors currently have available are not robust enough to reduce risk and help them managing uncertainty better. Machine learning data-driven approaches can bridge this gap, as they already do in the hedge fund industry. These approaches are now possible because data from thousands of companies over the world is available through platforms such as Crunchbase. Previous academic efforts have focused only on predicting two classes of exits, i.e., being acquired by other company or offering shares to the public, using only one or a few subsets of explanatory variables. These events are typically related to high returns, but also higher risk, making hard for a venture fund to get repeatable and sustainable returns. On the contrary, we will try to predict more possible outcomes including a subsequent funding round or the closure of the company using a large set of signals. In this way, our approach would provide VC investors with more information to set up a portfolio with lower risk that may eventually achieve higher returns than those based on finding unicorns (i.e., companies with a valuation higher than one billion dollars). We will analyze the performance of several machine learning methods in a dataset of over 120,000 early-stage companies in a realistic setting that tries to predict their progress in a 3-year time window. Results show that machine learning can support venture investors in their decision-making processes to find opportunities and better assessing the risk of potential investments.

1 January 2009 in International Journal of Forecasting
Verified
Journal Article
Closed access
JAJavier Arroyo
Javier Arroyo
CMCarlos Maté
Carlos Maté

17 June 2010 in Computational Economics
Verified
Journal Article
Closed access
PDF file
JAJavier Arroyo
Javier Arroyo
RERosa Espínola
Rosa Espínola
CMCarlos Maté
Carlos Maté

15 February 2007 in Neural Processing Letters
Verified
Journal Article
Closed access
PDF file
AMAntonio Muñoz
Antonio Muñoz
CMCarlos Maté
Carlos Maté
JAJavier Arroyo
Javier Arroyo
ÁSÁngel Sarabia
Ángel Sarabia