Computational approaches and data analytics in financial services: A literature review

Andriosopoulos, Dimitris; Doumpos, Michael; Pardalos, Pãnos M.; Zopounidis, Constantin

doi:10.1080/01605682.2019.1595193

Cited by 48 publications

(53 citation statements)

References 263 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This lack is noted in surveys about the use of machine learning in credit risk [51] or even other forms of risk in finance [1]. Andriosopoulos et al [3] note that as the analytical models for credit risk analysis become more complex, their understandability becomes an important issue, particularly from a supervisory point of view. However, private companies are turning their attention to interpretability as evidences the Explainable Machine Learning Challenge sponsored by FICO, a well-known credit scoring company [52]- [54].…”

Section: Machine Learning and Credit Risk Modeling In P2p Lendingmentioning

confidence: 99%

“…Credit risk analysis typically relies on statistical models such as logistic regression, probit regression, discriminant analysis and Cox survival models, among others [1], [2]. These methods offer good performance, are easy to understand, and do not pose computational problems [3]. On the other hand, machine learning alternatives frequently offer a better predictive performance because they can identify more complex risk patterns [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending

Garzón

Arroyo

Caparrini³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

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.

show abstract

Section: Machine Learning and Credit Risk Modeling In P2p Lendingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending

Garzón

Arroyo

Caparrini³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The area of applying artificial intelligence and machine learning in portfolio construction and optimization for cryptocurrencies is considered a recent research area. It still needs further investigation to find the best strategy that suits cryptocurrencies while getting benefit from machine learning models and techniques used for other financial assets [47].…”

Section: Automated Tradingmentioning

confidence: 99%

Cryptocurrencies and Artificial Intelligence: Challenges and Opportunities

et al. 2020

View full text Add to dashboard Cite

Decentralized cryptocurrencies have gained a lot of attention over the last decade. Bitcoin was introduced as the first cryptocurrency to allow direct online payments without relying on centralized financial entities. The use of Bitcoin has vastly grown as a financial asset rather than just a tool for online payments. A lot of cryptocurrencies have been created since 2011 with Bitcoin dominating the cryptocurrencies' market. With plenty of cryptocurrencies being used as financial assets and with millions of trades being executed through different exchange services, cryptocurrencies are susceptible to trading problems and challenges similar to those traditionally encountered in the financial domain. Price and trend prediction, volatility prediction, portfolio construction and fraud detection are some examples related to trading. In addition, there are other challenges that are specific to the domain of cryptocurrencies such as mining, cybersecurity, anonymity and privacy. In this paper, we survey the application of artificial intelligence techniques to address these challenges for cryptocurrencies with their vast amount of daily transactions, trades and news that are beyond human capabilities to analyze and learn from. This paper discusses the recent research work done in this emerging area and compares them in terms of used techniques and datasets. It also highlights possible research gaps and some potential areas for improvement.

show abstract

“…It has also been integrated into the main decision-making processes, such as the analysis of risk at both corporate and individual levels, the monitoring of transactions, and even corporate reporting. The design of such information technology in financial services is governed by local laws and regulations [1].…”

Section: Introductionmentioning

confidence: 99%

Identifying Big Data’s Opportunities, Challenges, and Implications in Finance

et al. 2020

View full text Add to dashboard Cite

One of the latest innovations in business and technology is the use of big data, as daily data are generated by billions of events. The big data issue is now considered in the accountants and finance professionals’ field as one of the most important sources for the analysis of financial products and services. This study is very innovative, with our research aiming to identify the opportunities, challenges, and implications of big data in the finance area. It is our purpose to find competitive advantages in terms of the extent to which big data brings visible benefits, also pointing out the challenges that a company may face in this field, such as cases of customers’ data security or customer satisfaction processes. The identification of this kind of dynamics allows us to draw conclusions on the advantages of big data based on these analyses and big data’s deep impact on finance. In particular, big data is now commonly used by financial institutions and banks for analytical purposes in financial market contexts. We conducted an exploratory survey of the existing literature to highlight such connections. In the last part of our study, we also propose directions for future research.

show abstract

Computational approaches and data analytics in financial services: A literature review

Cited by 48 publications

References 263 publications

Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending

Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending

Cryptocurrencies and Artificial Intelligence: Challenges and Opportunities

Identifying Big Data’s Opportunities, Challenges, and Implications in Finance

Contact Info

Product

Resources

About