Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk

Abedin, Mohammad Zoynul; Chi, Guotai; Hájek, Petr; Zhang, Tong

doi:10.1007/s40747-021-00614-4

Cited by 38 publications

(8 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning imbalanced datasets for companies, [40] analyses SMOTE (Synthetic Minority Over-sampling Technique) and combined Weighted SMOTE with ensemble learning (random forest) in order to propose a solution to the cited problem for small business. Authors of [41] also used SMOTE to tackle the problem and reach good results.…”

Section: Related Work: Imbalanced Datasetsmentioning

confidence: 99%

Towards a Machine Learning-based Model for Corporate Loan Default Prediction

BERRADA,

BARRAMOU,

ALAMI

2024

IJACSA

View full text Add to dashboard Cite

As the core business of the banking system is to lend money and then get it back, loan default is one of the most crucial issues for commercial banks. With data analysis and artificial intelligence, extracting valuable information from historical data, to lower their losses, banks would be able to classify their customers and predict the probability of credit repayment instead of relying on traditional methods. As most actual research is focused on individuals' loans, the novelty of the present paper is to treat corporate loans. Its main objective is to propose a model to address the problem using selected machine learning algorithms to classify companies into two classes to be able to predict loan defaulters. This paper delves into the Corporate Loan Default Prediction Model (CLD PM), which is designed to forecast loan defaults in corporations. The model is grounded in the CRISP-DM process, commencing with comprehending corporate requirements and implementing classification techniques. The data acquisition and preparation phase are critical in testing the selected algorithms, which involve Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, XGBoost, and Adaboost. The model's efficacy is assessed using various metrics, namely Accuracy, Precision, Recall, F1 score, and AUC. Subsequently, the model is scrutinized using an actual dataset of loans for Moroccan real estate firms. The findings reveal that the Random Forest and XGBoost algorithms outperformed the others, with every metric surpassing 90%. This was accomplished by utilizing SMOTE as an oversampling method, given the dataset's imbalance. Furthermore, when concentrating on financial statements, selecting the five most significant financial ratios and the company's age, Random Forest was adept at predicting defaulters with good results: accuracy of 90%, precision of 75%, recall of 50%, F1 score of 60% and AUC of 77%.

show abstract

Section: Related Work: Imbalanced Datasetsmentioning

confidence: 99%

Towards a Machine Learning-based Model for Corporate Loan Default Prediction

BERRADA,

BARRAMOU,

ALAMI

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Finally, it multiplies the resultant new vector by a stochastic number and adds it to Xi. This process effectively augments the minority class samples, thereby mitigating the challenges posed by class imbalance [10]. Eq.…”

Section: Modelsmentioning

confidence: 99%

Analysis of Credit Default Prediction Based on Logistic Regression, Random Forest and KNN Model

Wen

2024

AEMPS

View full text Add to dashboard Cite

Addressing the prevalent issue of limited access to loans for individuals with inadequate or non-existent credit histories is imperative to foster financial inclusion and safeguard vulnerable populations from unscrupulous lenders. With the help of unique characteristics, this research seeks to improve financial accessibility for the unbanked population by creating a safe and satisfying financing environment. The paper uses an imbalanced dataset that was gathered from Kaggle to examine how machine learning techniques can be applied to forecast credit risk. specifically, Logistic Regression, Random Forest, KNN, and Synthetic Minority Over-sampling Technique (SMOTE) are utilized in this study. The findings reveal an enhancement in accuracy following the resolution of the imbalanced dataset challenge. By employing these machine learning models, the research seeks to not only bridge the credit gap for the underserved but also mitigate the risks associated with lending to individuals lacking conventional credit histories. A thorough strategy for managing credit risk in the context of financial inclusion is shown by the investigation of different algorithms and the application of methods. These results contribute to the discourse on leveraging machine learning to create more equitable lending practices, ensuring that the unbanked population can access financial resources responsibly.

show abstract

“…As a result, the above studies represent only stationary financial distress prediction models, neglecting the impact of concept drift in financial distress prediction. In fact, the area of dynamic financial distress prediction is attracting considerable interest due to its capacity to take into account the change in the distribution of financial data over time [1,57,58]. To capture the dynamics of the change, we used LSTM neural networks in this study.…”

Section: Financial Distress Prediction Using Linguistic Indicatorsmentioning

confidence: 99%

Speech emotion recognition and text sentiment analysis for financial distress prediction

Hájek

Munk

2023

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

In recent years, there has been an increasing interest in text sentiment analysis and speech emotion recognition in finance due to their potential to capture the intentions and opinions of corporate stakeholders, such as managers and investors. A considerable performance improvement in forecasting company financial performance was achieved by taking textual sentiment into account. However, far too little attention has been paid to managerial emotional states and their potential contribution to financial distress prediction. This study seeks to address this problem by proposing a deep learning architecture that uniquely combines managerial emotional states extracted using speech emotion recognition with FinBERT-based sentiment analysis of earnings conference call transcripts. Thus, the obtained information is fused with traditional financial indicators to achieve a more accurate prediction of financial distress. The proposed model is validated using 1278 earnings conference calls of the 40 largest US companies. The findings of this study provide evidence on the essential role of managerial emotions in predicting financial distress, even when compared with sentiment indicators obtained from text. The experimental results also demonstrate the high accuracy of the proposed model compared with state-of-the-art prediction models.

show abstract

Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk

Cited by 38 publications

References 65 publications

Towards a Machine Learning-based Model for Corporate Loan Default Prediction

Towards a Machine Learning-based Model for Corporate Loan Default Prediction

Analysis of Credit Default Prediction Based on Logistic Regression, Random Forest and KNN Model

Speech emotion recognition and text sentiment analysis for financial distress prediction

Contact Info

Product

Resources

About