Machine Learning for Financial Risk Management: A Survey

Mashrur, Akib; Luo, Wei; Zaidi, Nayyar Abbas; Robles-Kelly, Antonio

doi:10.1109/access.2020.3036322

Cited by 87 publications

(52 citation statements)

References 196 publications

(237 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Explainable AI has become a prerequisite for building the trust, and to drive adoption of AI systems in high stake domains such as finance crime, credit risks, healthcare which requires reliability, safety and fairness [42], [43] [18]. The regulations like General Data Protection Regulation (GDPR) [44] particularly 'Records of Processing Activities', and 'Right to be informed'; and California Consumer Private Act (CCPA) [45] have also imposed the interpretability and explainability mandates for most of the AI/ML solutions in regulatory compliance domain.…”

Section: Explainable Aimentioning

confidence: 99%

“…• Explainability -the models that give high prediction accuracy are usually non-interpretable in nature that makes it difficult to understand the reasoning behind the decisions made [42].…”

Section: Barriers For Adoption Of Ai/ml In Finance Crime Domainmentioning

confidence: 99%

“…• Applying Explainable AI techniques -It is a need of AML domain to have an Explanation of the decisions made by non-interpretable models [42], [106]. There are several explainable AI techniques researched so far, for example few of them - [86,[99][100][101], however to the best of our knowledge none of it is applied in AML domain yet.…”

Section: Future Research Directions For Aml Domainmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

et al. 2021

View full text Add to dashboard Cite

Money laundering has been a global issue for decades, which is one of the major threat for economy and society. Government, regulatory and financial institutions are combating it together in their respective capacity, however still billions of dollars in fines by authorities make the headlines in the news. High-speed internet services have enabled financial institutions to deliver better customer experience through multi-channel engagements, which has led to exponential growth in transactions and new avenues for laundering the money for fraudsters. Literature shows the usage of statistical methods, data mining and Machine Learning (ML) techniques for money laundering detection, but limited research on Deep Learning (DL) techniques, primarily due to lack of model interpretability and explainability of the decisions made. Several studies are conducted on application of ML for Anti-Money Laundering (AML), and Explainable Artificial Intelligence (XAI) techniques in general, but lacks the study on usage of DL techniques together with XAI. This paper aims to review the current state-of-the-art literature on DL together with XAI for identifying suspicious money laundering transactions and identify future research areas. Key findings of the review are, researchers have preferred variants of Convolutional Neural Networks, and AutoEncoder; graph deep learning together with natural language processing is emerging as an important technology for AML; XAI use is not seen in AML domain; 51% ML methods used in AML are non-interpretable, 58% studies used sample of old real data; key challenges for researchers are access to recent real transaction data and scarcity of labelled training data; and data being highly imbalanced. Future research directions are, application of XAI techniques to bring-out explainability, graph deep learning using natural language processing (NLP), unsupervised and reinforcement learning to handle lack of labelled data; and joint research programs between research community and industry to benefit from domain knowledge and controlled access to data.

show abstract

Section: Explainable Aimentioning

confidence: 99%

Section: Barriers For Adoption Of Ai/ml In Finance Crime Domainmentioning

confidence: 99%

Section: Future Research Directions For Aml Domainmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Generally, the construction of an economic structure based on innovation and entrepreneurship requires the support of the government and social institutions. However, compared with the entrepreneurs in developed countries, Chinese entrepreneurs have to play two roles, that is, they have to create economic miracles and adapt themselves to the Chinese market economy system ( Belás et al, 2018 ; Mashrur et al, 2020 ), which brings them great pressure. How to get Chinese entrepreneurs out of the pressure and promote the development of the entrepreneurial economy is a problem faced by ministries, entrepreneurs, and scholars ( Hermansson and Cecilia, 2018 ; Yao and Qin, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Financial Risk Prediction and Entrepreneurs’ Psychological Status Under Entrepreneurial Psychology

Liang¹,

Yang

Ruan

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

Entrepreneurship plays an important role in the development of national economy. The study aims to accelerate the construction of social and economic structure by improving the success rate of new entrepreneurs in the process of innovation and entrepreneurship. First, the related theories of financial risk prediction are introduced, and entrepreneurial psychological status and the psychological states on entrepreneurship are analyzed. Second, the current situation of entrepreneurial psychology of new entrepreneurs is analyzed through a questionnaire survey and model test. The results show that private enterprises account for the largest proportion, with a percentage of 58.14% of 125. In total, 32 Chinese-foreign joint ventures rank second and account for 14.88% of the total, and the scale of each type of enterprises accounts for 25%, respectively. The operating years of enterprises are mainly between 10 and 20 years. Among the enterprises surveyed, the significant level of entrepreneurial psychology and entrepreneurial opportunity of entrepreneurs is p = 0.000–0.01. It indicates that males’ psychological adjustment ability and entrepreneurial ability in the entrepreneurial process are higher than females’, and their entrepreneurial psychological states and entrepreneurial ability will improve with the growth of age, education levels, and positions. It is concluded that entrepreneurial psychological capital and entrepreneurial opportunity are significantly positively correlated with financial risk expectation. The research results prove the impact of financial risks on the entrepreneurial psychology of new entrepreneurs, and provide a reference for new entrepreneurs in predicting financial risks.

show abstract

“…It is beneficial to explore techniques in artificial intelligence (AI) and machine learning algorithms as portfolio construction strategies in fund management involving SAA and TAA approaches. AI and machine learning algorithms have been utilised to maximise the returns of constructed portfolios with self-learning and less human interventions [13], such as evolutionary computation [14 -16], genetic algorithms (GA) [14, 17,18], particle swarm optimization algorithm [19,20], fuzzy logic [21], reinforcement learning (RL) [22,23], and recurrent reinforcement learning (RRL) [1]. Fuzzy neural network is also used for market risk prediction [24], with such information being useful for portfolio construction.…”

Section: Introductionmentioning

confidence: 99%

Dynamic portfolio rebalancing through reinforcement learning

Lim

Cao

Quek

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Portfolio managements in financial markets involve risk management strategies and opportunistic responses to individual trading behaviours. Optimal portfolios constructed aim to have a minimal risk with highest accompanying investment returns, regardless of market conditions. This paper focuses on providing an alternative view in maximising portfolio returns using Reinforcement Learning (RL) by considering dynamic risks appropriate to market conditions through dynamic portfolio rebalancing. The proposed algorithm is able to improve portfolio management by introducing the dynamic rebalancing of portfolios with vigorous risk through an RL agent. This is done while accounting for market conditions, asset diversifications, risk and returns in the global financial market. Studies have been performed in this paper to explore four types of methods with variations in fully portfolio rebalancing and gradual portfolio rebalancing, which combine with and without the use of the Long Short-Term Memory (LSTM) model to predict stock prices for adjusting the technical indicator centring. Performances of the four methods have been evaluated and compared using three constructed financial portfolios, including one portfolio with global market index assets with different risk levels, and two portfolios with uncorrelated stock assets from different sectors and risk levels. Observed from the experiment results, the proposed RL agent for gradual portfolio rebalancing with the LSTM model on price prediction outperforms the other three methods, as well as returns of individual assets in these three portfolios. The improvements of the returns using the RL agent for gradual rebalancing with prediction model are achieved at about 27.9–93.4% over those of the full rebalancing without prediction model. It has demonstrated the ability to dynamically adjust portfolio compositions according to the market trends, risks and returns of the global indices and stock assets.

show abstract

Machine Learning for Financial Risk Management: A Survey

Cited by 87 publications

References 196 publications

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

Financial Risk Prediction and Entrepreneurs’ Psychological Status Under Entrepreneurial Psychology

Dynamic portfolio rebalancing through reinforcement learning

Contact Info

Product

Resources

About