scholarly journals Peer-to-peer loan acceptance and default prediction with artificial intelligence

2020 ◽  
Vol 7 (6) ◽  
pp. 191649
Author(s):  
J. D. Turiel ◽  
T. Aste
Keyword(s):  
Artificial Intelligence ◽  
Small Businesses ◽  
Default Risk ◽  
Deep Neural Networks ◽  
Support Vector ◽  
Second Phase ◽  
Risk Models ◽  
Two Phase ◽  
Test Set ◽  
Default Prediction

Logistic regression (LR) and support vector machine algorithms, together with linear and nonlinear deep neural networks (DNNs), are applied to lending data in order to replicate lender acceptance of loans and predict the likelihood of default of issued loans. A two-phase model is proposed; the first phase predicts loan rejection, while the second one predicts default risk for approved loans. LR was found to be the best performer for the first phase, with test set recall macro score of 77.4 % . DNNs were applied to the second phase only, where they achieved best performance, with test set recall score of 72 % , for defaults. This shows that artificial intelligence can improve current credit risk models reducing the default risk of issued loans by as much as 70 % . The models were also applied to loans taken for small businesses alone. The first phase of the model performs significantly better when trained on the whole dataset. Instead, the second phase performs significantly better when trained on the small business subset. This suggests a potential discrepancy between how these loans are screened and how they should be analysed in terms of default prediction.

scholarly journals Mouse Behavior Analysis Based on Artificial Intelligence as a Second-Phase Authentication System

Proceedings ◽  
2019 ◽  
Vol 21 (1) ◽  
pp. 29
Author(s):  
Daniel Garabato ◽  
Jorge Rodríguez García ◽  
Francisco J. Novoa ◽  
Carlos Dafonte
Keyword(s):  
Artificial Intelligence ◽  
Support Vector Machines ◽  
Support Vector ◽  
Second Phase ◽  
Authentication Protocols ◽  
Mouse Behavior ◽  
Authentication Mechanism ◽  
Vector Machines ◽  
Authentication System ◽  
Current Stage

Nowadays, a wide variety of computer systems use authentication protocols based on several factors in order to enhance security. In this work, the viability of a second-phase authentication scheme based on users’ mouse behavior is analyzed by means of classical Artificial Intelligence techniques, such as the Support Vector Machines or Multi-Layer Perceptrons. Such methods were found to perform particularly well, demonstrating the feasibility of mouse behavior analytics as a second-phase authentication mechanism. In addition, in the current stage of the experiments, the classification techniques were found to be very stable for the extracted features.

scholarly journals Risk prediction with office and ambulatory blood pressure using artificial intelligence

2020 ◽  
Author(s):  
Pedro Guimarães ◽  
Andreas Keller ◽  
Michael Böhm ◽  
Lucas Lauder ◽  
José L. Ayala ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Blood Pressure ◽  
Neural Networks ◽  
Ambulatory Blood Pressure ◽  
Deep Neural Networks ◽  
White Coat ◽  
Risk Scores ◽  
Support Vector ◽  
The Novel

AbstractBackgroundTo develop and validate a novel, machine learning-derived model for prediction of cardiovascular (CV) mortality risk using office (OBP) and ambulatory blood pressure (ABP), to compare its performance with existing risk scores, and to assess the possibility of predicting ABP phenotypes (i.e. white-coat, ambulatory and masked hypertension) utilizing clinical variables.MethodsUsing data from 63,910 patients enrolled in the Spanish ABP monitoring registry, machine-learning approaches (logistic regression, support vector machine, gradient boosted decision trees, and deep neural networks) and stepwise forward feature selection were used for the classification of the data.ResultsOver a median follow-up of 4.7 years, 3,808 deaths occurred from which 1,295 were from CV causes. The performance for all tested classifiers increased while adding up to 10 features and converged thereafter. For the prediction of CV mortality, deep neural networks yielded the highest clinical performance. The novel mortality prediction models using OBP (CV-MortalityOBP) and ABP (CV-MortalityABP) outperformed all other risk scores. The area under the curve (AUC) achieved by the novel approach, using OBP variables only, was already significantly higher when compared with the AUC of Framingham score (0.685 vs 0.659, p = 1.97×10−22), the SCORE (0.679 vs 0.613, p = 6.21×10−22), and ASCVD (0.722 vs 0.639, p = 8.03×10−30) risk score. However, prediction of CV mortality with ABP instead of OBP data led to a significant increase in AUC (0.781 vs 0.752, p = 1.73×10−42), accuracy, balanced accuracy and sensitivity. The sensitivity and specificity for detection of ambulatory, masked, and white-coat hypertension ranged between 0.653-0.661 and 0.573-0.651, respectively.ConclusionWe developed a novel risk calculator for CV death using artificial intelligence based on a large cohort of patients included in the Spanish ABP monitoring registry. The receiver operating characteristic curves for CV-MortalityOBP and CV-MortalityABP with deep neural networks models outperformed all other risk metrics. Prediction of CV mortality using ABP data led to a significant increase in performance metrics. The prediction of ambulatory phenotypes using clinical characteristics, including OBP, was limited.

scholarly journals Personal Credit Default Prediction Model Based on Convolution Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Xiang Zhou ◽  
Wenyu Zhang ◽  
Yefeng Jiang
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Roc Curve ◽  
Default Risk ◽  
Model Performance ◽  
Support Vector ◽  
Personal Credit ◽  
Default Prediction ◽  
Credit Default ◽  
Performance Evaluation Index

It has great significance for the healthy development of credit industry to control the credit default risk by using the information technology. For some traditional research about the credit default prediction model, more attention is paid to the model accuracy, while the business characteristics of the credit risk prevention are easy to be ignored. Meanwhile, to reduce the complicity of the model, the data features need be extracted manually, which will decrease the high-dimensional correlation among the analyzing data and then result in the low prediction performance of the model. So, in the paper, the CNN (convolutional neural network) is used to establish a personal credit default prediction model, and both ACC (accuracy) and AUC (the area under the ROC curve) are taken as the performance evaluation index of the model. Experimental results show the model ACC (accuracy) is above 95% and AUC (the area under the ROC curve) is above 99%, and the model performance is much better than the classical algorithm including the SVM (support vector machine), Bayes, and RF (random forest).

scholarly journals A novel approach for selective feature mechanism for two-phase intrusion detection system

2019 ◽  
Vol 14 (1) ◽  
pp. 101
Author(s):  
B Narendra Kumar ◽  
M S V Sivarama Bhadri Raju ◽  
B Vishnu Vardhan
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Performance Metrics ◽  
Detection System ◽  
Computational Time ◽  
Support Vector ◽  
Phase System ◽  
Second Phase ◽  
Two Phase ◽  
Linear Dependency

Intrusion Detection is an important aspect to secure the computing systems from different intrusions. To improve the accuracy and to reduce the computational time, this paper proposes a two-phase hybrid method based on the SVM and RNN. In addition, this paper also had a proposal to obtain a few sets of features with a feature selection technique in which the detection performance increases. For the two-phase system, two different feature selection techniques were proposed which solves both the linear dependency and non-linear dependency between the features. In the first phase, the RNN combines with the proposed Joint Mutual Information Maximization (JMIM) based feature selection and in the second phase, the Support Vector Machine (SVM) combines with correlation based feature selection. Extensive simulations are carried out over the proposed system using two different datasets, NSL-KDD and Kyoto2006+. The performance is measured through the performance metrics such as Detection Rate (DR), Precision, False Alarm Rate (FAR), Accuracy and F-Score. Furthermore, a comparative analysis with few recent hybrid frameworks is also enumerated. The obtained results signify the effectiveness of proposed method.

scholarly journals The Conflict between Strategic Method Application and Theoretical Knowledge in Small and Medium Sized Companies: The Case of the Czech Republic

2016 ◽  
Vol 17 (2) ◽  
pp. 101-108
Author(s):  
Jarmila Šebestová
Keyword(s):  
Czech Republic ◽  
Small Businesses ◽  
Practical Knowledge ◽  
Theory And Practice ◽  
Second Phase ◽  
Two Phase ◽  
Potential Conflict ◽  
The Czech Republic ◽  
University Level ◽  
The University

The purpose of the paper and presented research is to discover the potential conflict between often used managerial methods and the recommended methods for small businesses to find the gap between theory and practice in order to support cooperation between entrepreneurs and the university in the area of management education. The survey was conducted as a two phase project, in the first phase with 529 SMEs and with 214 SMEs in the second phase in the Czech Republic in 2012–2013 within the own research project. The main findings, presented in this paper focus on the conflict between practical knowledge, used in small businesses, when only 48.2% of companies in the first phase and 54.21% in the second phase used some of the methods commonly taught at university level such as controlling, benchmarking or TQM.

A HYBRID TWO-PHASE ALGORITHM FOR FACE RECOGNITION

2004 ◽  
Vol 18 (08) ◽  
pp. 1423-1435 ◽  
Author(s):  
FRANK Y. SHIH ◽  
KAI ZHANG ◽  
YAN-YU FU
Keyword(s):  
Face Recognition ◽  
Recognition Rate ◽  
Principal Component ◽  
Recognition Algorithm ◽  
Support Vector ◽  
Second Phase ◽  
Two Phase ◽  
Data Set ◽  
Linear Discriminant ◽  
Database Size

Scientists have developed numerous classifiers in the pattern recognition field, because applying a single classifier is not very conducive to achieve a high recognition rate on face databases. Problems occur when the images of the same person are classified as one class, while they are in fact different in poses, expressions, or lighting conditions. In this paper, we present a hybrid, two-phase face recognition algorithm to achieve high recognition rates on the FERET data set. The first phase is to compress the large class number database size, whereas the second phase is to perform the decision-making. We investigate a variety of combinations of the feature extraction and pattern classification methods. Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Support Vector Machine (SVM) are examined and tested using 700 facial images of different poses from FERET database. Experimental results show that the two combinations, LDA+LDA and LDA+SVM, outperform the other types of combinations. Meanwhile, when classifiers are considered in the two-phase face recognition, it is better to adopt the L1 distance in the first phase and the class mean in the second phase.

A Comparison of Tem and Apfim to the Interpretation of Modulated Microstructures

1985 ◽  
Vol 43 ◽  
pp. 70-71
Author(s):  
M.G. Burke ◽  
M.K. Miller
Keyword(s):  
Low Temperature ◽  
Microstructural Characterization ◽  
Superlattice Reflection ◽  
High Volume ◽  
Atom Probe ◽  
Dark Field ◽  
Miscibility Gap ◽  
Second Phase ◽  
Two Phase ◽  
Probe Field

Interpretation of fine-scale microstructures containing high volume fractions of second phase is complex. In particular, microstructures developed through decomposition within low temperature miscibility gaps may be extremely fine. This paper compares the morphological interpretations of such complex microstructures by the high-resolution techniques of TEM and atom probe field-ion microscopy (APFIM).The Fe-25 at% Be alloy selected for this study was aged within the low temperature miscibility gap to form a <100> aligned two-phase microstructure. This triaxially modulated microstructure is composed of an Fe-rich ferrite phase and a B2-ordered Be-enriched phase. The microstructural characterization through conventional bright-field TEM is inadequate because of the many contributions to image contrast. The ordering reaction which accompanies spinodal decomposition in this alloy permits simplification of the image by the use of the centered dark field technique to image just one phase. A CDF image formed with a B2 superlattice reflection is shown in fig. 1. In this CDF micrograph, the the B2-ordered Be-enriched phase appears as bright regions in the darkly-imaging ferrite. By examining the specimen in a [001] orientation, the <100> nature of the modulations is evident.

THE DYNAMIC FRACTURE OF TWO PHASE ALLOYS WITH SECOND PHASE INCLUSIONS

1985 ◽  
Vol 46 (C5) ◽  
pp. C5-251-C5-255
Author(s):  
S. Pytel ◽  
L. Wojnar
Keyword(s):  
Dynamic Fracture ◽  
Second Phase ◽  
Two Phase

Behaviour of air injection nozzles in dissolved air flotation

1995 ◽  
Vol 31 (3-4) ◽  
pp. 25-35 ◽  
Author(s):  
E. M. Rykaart ◽  
J. Haarhoff
Keyword(s):  
Bubble Coalescence ◽  
Second Phase ◽  
Initial Growth ◽  
Two Phase ◽  
Dissolved Air Flotation ◽  
Nozzle Orifice ◽  
Pressure Release ◽  
Air Volume ◽  
Air Flotation ◽  
Dissolved Air

A simple two-phase conceptual model is postulated to explain the initial growth of microbubbles after pressure release in dissolved air flotation. During the first phase bubbles merely expand from existing nucleation centres as air precipitates from solution, without bubble coalescence. This phase ends when all excess air is transferred to the gas phase. During the second phase, the total air volume remains the same, but bubbles continue to grow due to bubble coalescence. This model is used to explain the results from experiments where three different nozzle variations were tested, namely a nozzle with an impinging surface immediately outside the nozzle orifice, a nozzle with a bend in the nozzle channel, and a nozzle with a tapering outlet immediately outside the nozzle orifice. From these experiments, it is inferred that the first phase of bubble growth is completed at approximately 1.7 ms after the start of pressure release.

Sign in / Sign up

Export Citation Format

Share Document