Assessing credit risk of commercial customers using hybrid machine learning algorithms

Machado, Marcos Roberto; Karray, Salma

doi:10.1016/j.eswa.2022.116889

Cited by 72 publications

(21 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining unsupervised and supervised machine learning (ML) methods, one study evaluated credit risk for commercial customers. Hybrid models outperformed individual supervised ML models, particularly in complex scenarios with nonlinear predictor-target relationships [6]. Building on these findings, the study anticipates that preceding mixture-of-experts neural networks with an unsupervised clusterer will enhance overall model accuracy.…”

Section: Introductionmentioning

confidence: 65%

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

Makokha,

Kube,

Ngesa

2024

JDAIP

View full text Add to dashboard Cite

Peer-to-peer (P2P) lending offers an alternative way to access credit. Unlike established lending institutions with proven credit risk management practices, P2P platforms rely on numerous independent variables to evaluate loan applicants' creditworthiness. This study aims to estimate default probabilities using a mixture-of-experts neural network in P2P lending. The approach involves coupling unsupervised clustering to capture essential data properties with a classification algorithm based on the mixture-of-experts structure. This classic design enhances model capacity without significant computational overhead. The model was tested using P2P data from Lending Club, comparing it to other methods like Logistic Regression, AdaBoost, Gradient Boosting, Decision Tree, Support Vector Machine, and Random Forest. The hybrid model demonstrated superior performance, with a Mean Squared Error reduction of at least 25%.

show abstract

Section: Introductionmentioning

confidence: 65%

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

Makokha,

Kube,

Ngesa

2024

JDAIP

View full text Add to dashboard Cite

show abstract

“…The active compounds against KRAS G12 mutant with experimentally determined IC50 values were retrieved from the Binding DB [ 17 ]. The compounds in SDF format were imported to MOE software.…”

Section: Methodsmentioning

confidence: 99%

Prospective virtual screening combined with bio-molecular simulation enabled identification of new inhibitors for the KRAS drug target

Ajmal,

Alkhatabi,

Alreemi

et al. 2024

BMC Chemistry

View full text Add to dashboard Cite

Lung cancer is a disease with a high mortality rate and it is the number one cause of cancer death globally. Approximately 12–14% of non-small cell lung cancers are caused by mutations in KRASG12C. The KRASG12C is one of the most prevalent mutants in lung cancer patients. KRAS was first considered undruggable. The sotorasib and adagrasib are the recently approved drugs that selectively target KRASG12C, and offer new treatment approaches to enhance patient outcomes however drug resistance frequently arises. Drug development is a challenging, expensive, and time-consuming process. Recently, machine-learning-based virtual screening are used for the development of new drugs. In this study, we performed machine-learning-based virtual screening followed by molecular docking, all atoms molecular dynamics simulation, and binding energy calculations for the identifications of new inhibitors against the KRASG12C mutant. In this study, four machine learning models including, random forest, k-nearest neighbors, Gaussian naïve Bayes, and support vector machine were used. By using an external dataset and 5-fold cross-validation, the developed models were validated. Among all the models the performance of the random forest (RF) model was best on the train/test dataset and external dataset. The random forest model was further used for the virtual screening of the ZINC15 database, in-house database, Pakistani phytochemicals, and South African Natural Products database. A total of 100 ns MD simulation was performed for the four best docking score complexes as well as the standard compound in complex with KRASG12C. Furthermore, the top four hits revealed greater stability and greater binding affinities for KRASG12C compared to the standard drug. These new hits have the potential to inhibit KRASG12C and may help to prevent KRAS-associated lung cancer. All the datasets used in this study can be freely available at (https://github.com/Amar-Ajmal/Datasets-for-KRAS).

show abstract

“…The Elbow statistical method is used to determine the optimal number of clusters, i.e., k, since the number k can be selected intuitively in the k-means clustering algorithm. The Elbow statistical method is based on the sum of the squared distances between the data points and their corresponding cluster centroid [50]. The inertia measures the clustering degree of a dataset using the k-means clustering algorithm.…”

Section: Renewable Resource Analysis Using K-means Clustering Algorithmmentioning

confidence: 99%

Optimal Design of Hybrid Microgrid in Isolated Communities of Ecuador

A. Pesantes,

Hidalgo-Leon,

Rengifo

et al. 2024

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

In rural territories, the communities use energy sources based on fossil fuels to supply themselves with electricity, which may address two main problems: greenhouse gas emissions and high fuel prices. Hence, there is an opportunity to include renewable resources in the energy mix. This paper develops an optimization model to determine the optimal sizing, the total annual investment cost in renewable generation, and other operating costs of the components of a hybrid microgrid. By running a k-means clustering algorithm on a meteorological dataset of the community under study, the hourly representative values become input parameters in the proposed optimization model. The method for the optimal design of hybrid microgrid is analyzed in six operating scenarios considering: ① 24-hour continuous power supply; ② load shedding percentage; ③ diesel power generator (genset) curtailment; ④ the worst meteorological conditions; ⑤ the use of renewable energy sources including battery energy storage systems (BESSs)； and ⑥ the use of genset. A mathematical programming language (AMPL) tool is used to find solutions of the proposed optimization model. Results show that the total costs of microgrid in the scenarios that cover 100% of the load demand (without considering the scenario with 100% renewables) increase by over 16% compared with the scenario with genset operation limitation. For the designs with power supply restrictions, the total cost of microgrid in the scenario with load shedding is reduced by over 27% compared with that without load shedding.

show abstract

Assessing credit risk of commercial customers using hybrid machine learning algorithms

Cited by 72 publications

References 70 publications

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

A Hybrid Approach for Predicting Probability of Default in Peer-to-Peer (P2P) Lending Platforms Using Mixture-of-Experts Neural Network

Prospective virtual screening combined with bio-molecular simulation enabled identification of new inhibitors for the KRAS drug target

Optimal Design of Hybrid Microgrid in Isolated Communities of Ecuador

Contact Info

Product

Resources

About