Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Biao Xu et al.
Summary: Fraud detection is the process of identifying, monitoring, and preventing potentially fraudulent activities from complex data. This study proposes a novel approach, deep boosting decision trees (DBDT), for fraud detection based on gradient boosting and neural networks. The method combines the advantages of conventional methods and deep learning, improving representation learning capability and maintaining interpretability. Experimental results demonstrate that DBDT significantly improves performance while maintaining good interpretability.
DECISION SUPPORT SYSTEMS
(2023)
Article
Business
Waymond Rodgers et al.
Summary: This paper introduces a new approach to understanding bankers' risk-taking behavior by using behavioral finance and a unique decision-making model. The results indicate that bankers' risk assessments differ in evaluating financial information regarding loans.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Business
Indranil Ghosh et al.
Summary: This paper analyzes the high-frequency 1-minute intraday movements of closing prices for Bitcoin, crude oil, the Dow Jones Industrial Average (DJIA), and the euro-U.S. dollar exchange rate during different non-overlapping regimes spanning the COVID-19 pandemic. The study evaluates the empirical characteristics of these assets using nonlinear modeling tools and tests. The proposed methodology employs maximal overlap discrete wavelet transformation, Bayesian structural time series forecasting, and random walk with drift to assess the predictability of selected variables across different phases of the pandemic. The findings indicate that all variables can be accurately forecasted, despite chaotic traces, during different sub-regimes, overcoming the adverse effects of the pandemic's first and second waves. High-frequency movements of Bitcoin and the euro-U.S. dollar exchange rates show relatively better predictability, demonstrating resilience during the pandemic. Ultimately, this research outcome will contribute to mitigating financial risk during volatile periods.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Business
Elie Bouri et al.
Summary: The importance of climate risk in financial markets and decision-making is increasing. This study examines the predictability of two climate risk measures - transition risk and physical risk - on the returns and volatility of energy stocks, carbon emissions allowances, and green bonds. The results show that transition risk has a stronger predictability on returns and volatility, particularly for brown energy stocks and carbon emissions allowances. The predictability varies across different periods and market conditions. This study has implications for climate risk assessment, portfolio decarbonization, and climate risk management under COP26.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Management
Joao A. Bastos et al.
Summary: This study suggests that banks do not need to compromise predictive accuracy for model transparency in credit risk management. The predictions of credit losses from black-box models can be easily explained in terms of their inputs. Banks should consider the determinants of credit losses suggested by these models in lending decisions and pricing of credit exposures.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Automation & Control Systems
Fan Yang et al.
Summary: This article proposes an architecture for privacy-preserved credit data and model sharing, optimizing data privacy by sharing data models and ensuring secure storage through the use of deletable Bloom filters. It also introduces authority control and credit verification contracts for secure certification of credit sharing model results.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Management
Elena Dumitrescu et al.
Summary: In the context of credit scoring, a high-performance and interpretable credit scoring method called penalised logistic tree regression (PLTR) is proposed, which uses information from decision trees to improve logistic regression performance, allowing for capturing non-linear effects in credit scoring data while maintaining interpretability.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Agriculture, Multidisciplinary
Liang Han et al.
Summary: This study uses machine learning models based on remote sensing images to detect crop lodging. The study uses Synthetic Minority Oversampling Technique and Edited Nearest Neighbors to handle imbalanced datasets, and proposes the SMOTE-ENN-XGBoost model for identifying maize lodging at the plot scale. SHapley Additive exPlanations approach is employed to interpret the features that determine lodging classification and activity prediction. The results suggest that canopy structure, spectral, and textural features should be considered simultaneously for accurate detection of crop lodging in crop breeding programs.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Computer Science, Artificial Intelligence
Hongyi Qian et al.
Summary: This paper introduces a heuristic algorithm based on permutation importance (PIMP) to correct the bias in feature importance in financial distress prediction models, improving the performance of machine learning models by removing redundant features and making the results more interpretable.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Operations Research & Management Science
Md. Iftekharul Alam Efat et al.
Summary: Existing sales forecasting models are not comprehensive and flexible enough to consider dynamic changes and nonlinearities in sales time-series. This study proposes a hybrid model that combines adaptive trend estimated series (ATES) with a deep neural network model to capture different big data characteristics in sales forecasting data. The proposed hybrid model outperforms existing models for forecasting horizons ranging from one to 12 months.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Operations Research & Management Science
Yang Lu et al.
Summary: This paper proposes a credit risk feature selection approach that integrates the binary opposite whale optimization algorithm and the Kolmogorov-Smirnov statistic. Empirical results show that the BOWOA-KS model outperforms other methods in improving SMEs' creditworthiness and access to loans.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Futian Weng et al.
Summary: This study examines the impact of financial pressure on forecasting the volatility of health care stock and finds that it improves the predictive performance for both China and the USA. XGBoost model outperforms other benchmark models, and the findings have implications for financial institutions and investors.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Sangjin Park et al.
Summary: This study provides two approaches, a deep learning model based on the LSTM network architecture and an interpretable machine learning model, for better economic prediction and decision-making. The research found that private debt in developed economies and government debt in emerging economies are major factors limiting future economic growth. In terms of the economic impact of COVID-19, reduced interest rates and increased government debt have increased the probability of a crisis in some emerging economies in the future.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Multidisciplinary Sciences
Anne-Marie Nussberger et al.
Summary: The study finds that non-experts have positive attitudes towards the interpretability of AI, especially in decisions with high stakes and scarce resources. However, they tend to sacrifice interpretability when it conflicts with accuracy.
NATURE COMMUNICATIONS
(2022)
Article
Business
Juram Kim et al.
Summary: This study develops an analytical framework for expert-machine collaborations in technology valuation using interpretable machine learning. By constructing a technological characteristics-economic value matrix, developing machine learning models to examine the relationships between technological characteristics and economic value, and explaining the influence of technological characteristics using the SHapley Additive exPlanation method, the framework proves to be a useful complementary tool for technology valuation based on a case study of technologies from Stanford University's Office of Technology Licensing.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2022)
Article
Mathematical & Computational Biology
Yue Li et al.
Summary: This paper proposes a hybrid intrusion detection method that utilizes ADASYN and ID3 decision tree to improve the effectiveness of intrusion detection rate. The model based on ADASYN and ID3 decision tree achieves higher accuracy and lower false alarm rate, making it more suitable for intrusion detection tasks.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Mattia Setzu et al.
Summary: Artificial Intelligence (AI) is widely used in various aspects of society, including in complex tasks where machine learning models show remarkable accuracy but lack interpretability. GLocalX is a local-first explanation method that aggregates local explanations to provide insight into black box models.
ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jong Wook Lee et al.
Summary: A credit default prediction model based on graph convolutional network (GCN) is proposed in this study, which can reflect nonlinear relationships between borrower's attributes and default risk. By separately employing three types of information for relations between borrowers, the model outperforms existing classification models and identifies the relative contribution of input attributes.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Operations Research & Management Science
Mohammad Mahbobi et al.
Summary: This study introduces a comprehensive algorithm to improve the accuracy of default payment prediction by utilizing various oversampling and undersampling strategies, implementing classification models to accurately classify minority class data, and demonstrating the algorithm's advantages in dealing with imbalanced data.
ANNALS OF OPERATIONS RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Elif Ceren Gok et al.
Summary: The serious Covid-19 pandemic has impacts on health, economy, society, with fast and accurate diagnosis being crucial. A study utilizing machine learning algorithms on blood samples from patients in Einstein Hospital in Brazil achieved high accuracy in predicting the severity of Covid-19.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Min Sue Park et al.
Summary: With the increasing amount of data, there is a growing demand for utilizing machine learning methodologies in bankruptcy prediction. This study focuses on the interpretability of machine learning models, particularly measuring feature importance using the LIME algorithm, to address the black-box issue.
Article
Business
Sulin Pang et al.
Summary: This article proposes a credit scoring model based on extreme learning machine, fuzzy c-means algorithm, and confusion matrix calculation to evaluate credit qualities of borrowers and predict default behavior. Experimental results show high accuracy of the established model, providing scientific guidance and important reference values for financial institutions.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Computer Science, Artificial Intelligence
Rogelio A. Mancisidor et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
X. W. Liang et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Business
Jing-Ping Li et al.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2020)
Article
Computer Science, Information Systems
Talha Mahboob Alam et al.
Article
Business
Muhammad Ali Nasir
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2020)
Article
Computer Science, Artificial Intelligence
Hussein A. Abdou et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Management
George S. Atsalakis et al.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2019)
Article
Business, Finance
Mohammad Zoynul Abedin et al.
INTERNATIONAL JOURNAL OF FINANCE & ECONOMICS
(2019)
Article
Economics
Avi Goldfarb et al.
JOURNAL OF ECONOMIC LITERATURE
(2019)
Article
Computer Science, Artificial Intelligence
David Veganzones et al.
DECISION SUPPORT SYSTEMS
(2018)
Article
Business
Chi Guotai et al.
JOURNAL OF BUSINESS ECONOMICS AND MANAGEMENT
(2017)
Article
Social Sciences, Interdisciplinary
Fahmida E. Moulal et al.
RISK MANAGEMENT-AN INTERNATIONAL JOURNAL
(2017)
Article
Hospitality, Leisure, Sport & Tourism
Hui Li et al.
INTERNATIONAL JOURNAL OF HOSPITALITY MANAGEMENT
(2013)
Article
Management
Hong Sik Kim et al.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2010)
Article
Computer Science, Information Systems
Donghai Guan et al.
INFORMATION SCIENCES
(2009)