Predicting mortgage early delinquency with machine learning methods

Chen, Shunqin; Guo, Zhengfeng; Zhao, Xinlei

doi:10.1016/j.ejor.2020.07.058

Cited by 37 publications

(15 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The random forest model has the advantages of fewer adjustment parameters, high prediction accuracy and good generalization ability, which can effectively avoid the phenomenon of "overfitting", and has good robustness in extracting the features of the data set. It has great advantages in dealing with large-scale data sets and high-dimensional feature vector space, and has been widely used in the fields of medicine and economics [38,39]. This paper involves processing of multiple data from several indicators, and the application of this method for safety evaluation and scenario prediction is more accurate.…”

Section: Random Forest Modelmentioning

confidence: 99%

Evaluation and Scenario Prediction of the Water-Energy-Food System Security in the Yangtze River Economic Belt Based on the RF-Haken Model

Chen

2021

Water

View full text Add to dashboard Cite

As an important agricultural production area in China, the Yangtze River Economic Belt has a large amount of water resources and rich types of energy. Water and energy resources are the supporting basis of food production, and the production and use of energy also need to consume a large amount of water resources. The three affect each other and are interdependent. Paying attention to the synergistic security of water-energy-food system in the Yangtze River Economic Belt is important for regional economic development. This paper uses the pressure-state-response (PSR) model and selects 27 indicators to build an evaluation index system of the regional water-energy-food system. We use the random forest model to evaluate the security level of the Yangtze River Economic Belt from 2008 to 2017, and the Haken model is employed to identify the driving factors that dominate the synergistic evolution of the system. Then we take the identified factors as the key control variables under each scenario and launch a scenario simulation of some provinces in the Yangtze River Economic Belt in 2025. The results show that due to the improvement of water and energy utilization efficiency and the advancement of agricultural production technology, the level of water-energy-food security in the Yangtze River Economic Belt improved significantly from 2008 to 2017. Each province performs differently in different subsystems, with water resources security being better in the upper reaches and Zhejiang and Shanghai in the lower reaches, and food security being better in the middle and lower reaches. The level of energy security is high in Sichuan, Yunnan, and Guizhou in the upper reaches and Shanghai and Anhui in the lower reaches. According to the results of scenario prediction for Jiangsu Province and Hubei Province in 2025, implementing moderate management in accordance with current management objectives can increase the overall security of the system to level 4. The two provinces should focus on controlling water resources and energy consumption and improving the utilization efficiency of water and energy in agricultural production.

show abstract

Section: Random Forest Modelmentioning

confidence: 99%

Evaluation and Scenario Prediction of the Water-Energy-Food System Security in the Yangtze River Economic Belt Based on the RF-Haken Model

Chen

2021

Water

View full text Add to dashboard Cite

show abstract

“…Some machine learning approaches [ 21 , 22 , 23 , 24 , 25 , 26 , 27 ] have been developed to improve classification performance further. Analysis of performance quality and tuning effects of the machine-learning techniques was presented in [ 21 ], in which Adaboost ensembles were more easily optimized than the other techniques.…”

Section: Introductionmentioning

confidence: 99%

“…Analysis of performance quality and tuning effects of the machine-learning techniques was presented in [ 21 ], in which Adaboost ensembles were more easily optimized than the other techniques. The performance of thirteen methods was investigated for modelling and predicting mortgage early delinquency probabilities [ 22 ]. Heterogeneous ensemble methods lead to other methods in the training, out-of-sample, and out-of-time datasets in terms of risk classification.…”

Section: Introductionmentioning

confidence: 99%

Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification

Huang

Guan

2021

Sensors

View full text Add to dashboard Cite

A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones.

show abstract

“…To assess the influence of borrowers' income on the occurrence of overdue debt on residential mortgage, scientific literature uses such indicators as the size of the loan [14,15,11,7,16,17,18]; loan term [19,14,15,12]; interest rate on residential mortgage [19,14,12,8,11,7,20]; unemployment rate / employment rate [14,7,12,16,8,17,21]; Gini coefficient [7,16]. At the same time, studies devoted to assessing the impact of the volatility of incomes of the Russian population on banking residetial mortgage are not fully represented in the scientific literature.…”

Section: Introductionmentioning

confidence: 99%

Household Incomes and Bank Residential Mortgage in Russia

2021

View full text Add to dashboard Cite

The influence of the incomes of the population subject to changes on bank mortgage lending was investigated using the methods of correlation and regression analysis. Three approaches to income volatility as an indicator of their volatility have been implemented: variability within certain time periods through an assessment of the coefficients of variation during the year, between periods through an assessment of the average annual income growth rates, and the variability of the distribution between income recipients through inequality indicators. According to the research results, indicators of bank residential mortgage are more strongly associated with variations in nominal income than in real one; the low level of overdue mortgage debt in the Russian banking sector is determined by a qualitative assessment of borrowers' capabilities in accordance with their income; an increase in income volatility is accompanied by a decrease in the share of overdue mortgage debt. The stability of the population's income contributes to an increase in the number and total volume of bank residential mortgage. As a result of econometric modeling, the maximum significant effect of the unemployment rate on the share of overdue mortgage debt has been established.

show abstract

Predicting mortgage early delinquency with machine learning methods

Cited by 37 publications

References 25 publications

Evaluation and Scenario Prediction of the Water-Energy-Food System Security in the Yangtze River Economic Belt Based on the RF-Haken Model

Evaluation and Scenario Prediction of the Water-Energy-Food System Security in the Yangtze River Economic Belt Based on the RF-Haken Model

Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification

Household Incomes and Bank Residential Mortgage in Russia

Contact Info

Product

Resources

About