An Optimised Greedy-Weighted Ensemble Framework for Financial Loan Default Prediction

Ezekiel Nii Noye Nortey; Jones Asante-Koranteng; Marcellin Atemkeng; Theophilus Ansah-Narh; David Mensah; Rebecca Davis; Ravenhill Adjetey Laryea

cs.LGMar 19, 2026

An Optimised Greedy-Weighted Ensemble Framework for Financial Loan Default Prediction

Authors: Ezekiel Nii Noye Nortey, Jones Asante-Koranteng, Marcellin Atemkeng, Theophilus Ansah-Narh, David Mensah, Rebecca Davis, Ravenhill Adjetey Laryea

Organizations: Department of Statistics and Actuarial Science, University of Ghana, P. O. Box LG 115, Legon, Accra, Ghana. · Department of Statistics, Tali Graduate school, Dominion University College, P. O. Box LG 80, Legon, Accra,Ghana. · Department of Mathematics, Rhodes University, P.O. Box 94, Makhanda, 6140, Grahamstown, South Africa. · National Institute for Theoretical and Computational Sciences (NITheCS), Stellenbosch 7600, South Africa. · Ghana Space Science and Technology Institute, Ghana Atomic Energy Commission, P. O. Box LG 80, Legon, Accra, Ghana. · Department of Mathematics and Actuarial Science, Pentecost University, P.O. Box KN 1739, Kaneshie, Accra, Ghana. · Department of Economics and Actuarial Science, University of Professional Studies, P. O. Box LG 149, Legon, Accra, Ghana.

Abstract

Accurate prediction of loan defaults is a central challenge in credit risk management, particularly in modern financial datasets characterised by nonlinear relationships, class imbalance, and evolving borrower behaviour. Traditional statistical models and static ensemble methods often struggle to maintain reliable performance under such conditions. This study proposes an Optimised Greedy-Weighted Ensemble framework for loan default prediction that dynamically allocates model weights based on empirical predictive performance. The framework integrates multiple machine learning classifiers, with their hyperparameters first optimised using Particle Swarm Optimisation. Model predictions are then combined via a regularised greedy weighting mechanism. At the same time, a neural-network-based meta-learner is employed within stacked-ensemble to capture higher-order relationships among model outputs. Experiments conducted on the Lending Club dataset demonstrate that the proposed framework improves predictive performance compared with individual classifiers. The BlendNet ensemble achieved the strongest results with an AUC of 0.80, a macro-average F1-score of 0.73, and a default recall of 0.81. Calibration analysis further shows that tree-based ensembles such as Extra Trees and Gradient Boosting provide the most reliable probability estimates, while the stacked ensemble offers superior ranking capability. Feature analysis using Recursive Feature Elimination identifies revolving utilisation, annual income, and debt-to-income ratio as the most influential predictors of loan default. These findings demonstrate that performance-driven ensemble weighting can improve both predictive accuracy and interpretability in credit risk modelling. The proposed framework provides a scalable data-driven approach to support institutional credit assessment, risk monitoring, and financial decision-making.

Figures & tables

Paradigm	Core Principle	Strengths	Key Limitations for Credit Risk Prediction
Bagging	Independent models trained on bootstrap samples and aggregated through voting or averaging	Reduces variance and improves model stability	Typically assigns equal or heuristic weights to base learners, limiting adaptability under concept drift and evolving borrower behaviour
Boosting	Sequential training where each learner focuses on correcting previous errors	Strong predictive accuracy and ability to capture nonlinear patterns	Sequential dependence may amplify noise or instability; primarily reweights observations rather than dynamically reallocating model importance
Stacking	Meta-learner combines predictions from heterogeneous base models	High predictive flexibility and ability to exploit model diversity	Model contributions are often implicit and opaque; limited mechanisms for adapting model influence under changing data regimes
Proposed GWE	Performance-driven greedy optimisation of ensemble weights	Adaptive model weighting, improved interpretability, and robustness to evolving data distributions	Designed to overcome static weighting, sequential dependence, and opacity limitations present in traditional ensembles

Table 1: Comparison of ensemble paradigms and their limitations in credit risk modelling

\mathbf{v}_{i}=w\cdot\mathbf{v}_{i}+c_{1}\cdot\text{rand}_{1}\cdot(\mathbf{p}_{i}^{best}-\mathbf{p}_{i})+c_{2}\cdot\text{rand}_{2}\cdot(\mathbf{g}^{best}-\mathbf{p}_{i})

Algorithm 1 PSO for hyperparameter tuning

Base model	Defined hyperparameter space	Best optimal parameter (via PSO)
GB	n_estimators: (50, 200), max_depth: (3, 10), learning_rate: (0.01, 0.1)	n_estimators: 150, max_depth: 5, learning_rate: 0.05
MLP	hidden_layer_sizes: (50, 200), alpha: (0.0001, 0.01)	hidden_layer_sizes: 150, alpha: 0.005
SVM	C: (0.1, 10), gamma: (0.001, 0.1)	C: 3, gamma: 0.05
KNN	n_neighbors: (3, 20)	n_neighbors: 10
LR	C: (0.1, 10)	C: 1.5
Extra Trees	n_estimators: (50, 200), max_depth: (10, 20), min_samples_split: (2, 10)	n_estimators: 120, max_depth: 15, min_samples_split: 4

Table 2: Comparison of hyperparameter spaces and optimal values for different base models tuned using PSO

Panel of Figure 3 — Figure 3.1 : Flowchart illustrating the BlendNet meta-learning process within the stacked ensemble framework.

	Items	Description
0	loan_amnt	The specified loan amount requested by the borrower
1	term	The quantity of installments for the loan
2	int_rate	Loan’s interest rate
3	installment	The borrower’s monthly payment obligation
4	grade	Loan grade assigned by LC
5	sub_grade	Subgrade designation for LC-assigned loans

Table 3: Description of loan variables.

Figure 4.1 : Distribution of missing values across features with gaps in the Lending Club dataset.

	count	mean	std	min	25%	50%	75%	max
loan_amnt	335867.00	14522.76	8386.60	1000.00	8000.00	12400.00	20000.00	40000.00
int_rate	335867.00	13.80	4.51	5.32	10.64	13.35	16.78	30.99
installment	335867.00	445.16	251.59	28.75	263.78	388.20	583.79	1533.81
annual_inc	335867.00	75817.04	61972.24	5000.00	47000.00	65000.00	90000.00	8706582.00
dti	335867.00	17.72	8.15	0.00	11.63	17.25	23.42	380.53
open_acc	335867.00	11.60	5.18	1.00	8.00	11.00	14.00	90.00

Table 4: Summary statistics for loan default related variables.

Figure 4.2 : Violin plots showing the distribution and variability of key numerical features in the Lending Club dataset. The plots reveal the central tendency, spread, and potential outliers within each feature, providing insights into the characteristics of the borrowers and loans.

Figure 4.3 : Heatmap of Pearson correlation coefficients among key numerical features in the Lending Club dataset, emphasising statistically significant relationships influencing loan default risk.

Figure 4.4 : Comparison of loan outcomes–fully paid or charged off-based on borrower-provided number of payments (Panel A), home ownership status (Panel B), loan verification status (Panel C), and loan request category (Panel D).

Figure 4.5 : The left panel shows the distribution of fully paid and charged-off loans across different employment lengths. The right panel displays the top

30

job titles that were afforded a loan, highlighting the variety of professions represented in the dataset.

Figure 5.1 : Outlier Detection and Correction using the BCP-HI Pipeline: (Left) The original signal (annual_inc) showing significant spikes indicative of potential outliers. (Middle) The original signal with detected outliers marked as red dots. (Right) The corrected signal after outlier detection and correction displays a smoother, more reliable trend for further analysis.

Panel of Figure 5 — Figure 5.2 : Comparison of loan status plots: (a) illustrates the biased plot, while (b) showcases the unbiased plot, highlighting the impact of addressing data imbalance in depicting accurate loan status distributions.

X^{\prime}=\Phi^{-1}(F(X)),

Algorithm 5 Minority Class Enhancement Algorithm Using Statistical Data Augmentation

D=\{(X_{1},Y_{1}),(X_{2},Y_{2}),\ldots,(X_{N},Y_{N})\}

Algorithm 6 Recursive Feature Elimination with Model Classifier

Figure 5.3 : Feature importance analysis using RFE across four ensemble learning models–RF, LightGBM, XGBoost, and CatBoost. The plot highlights the most influential features for loan default prediction, showcasing the consistency and model-specific preferences for key predictors.

Figure 5.4 : Performance of classification models across different numbers of features using Recursive Feature Elimination with Cross-Validation.

Figure 6.1 : Performance comparison of base models and ensemble methods for predicting financial loan defaults: Confusion matrices highlighting classification accuracy across “Fully Paid” (Class

1

) and “Charged Off” (Class

0

) loans.

Figure 6.2 : Classification reports for base models and ensemble methods in loan default prediction. The figure compares precision, recall, and F1-scores for “Fully Paid” (Class 1) and “Charged Off” (Class 0) loans across all evaluated models.

Figure 6.3 : Bootstrapped ROC curves with

95\%

confidence intervals for all evaluated models. BlendNet achieves the highest AUC (

0.80\pm 0.10

), indicating superior discriminatory capability compared with both traditional classifiers and alternative ensemble strategies.

Figure 6.4 : Calibration curves for all evaluated models. ExtraTrees and Gradient Boosting demonstrate the best calibration behaviour, while several models show deviations from the ideal probability calibration line.

Study	Method	Key Metrics	Data Used
Singh (2023)	RF, SVM, NN, GBoost	AUC: 59% $\rightarrow$ 93%, Recall: 56% $\rightarrow$ 89%; F1-Macro: 56% $\rightarrow$ 88%	Lending Club
Turiel and Aste (2019)	LR, SVM, LNN, DNN	AUC: 64% $\rightarrow$ 69%, Recall: 62% $\rightarrow$ 72%	Lending Club
Zhu et al. (2019)	LR, SVM, DTree, RF	AUC: 74% $\rightarrow$ 98%, Recall: 74% $\rightarrow$ 98%;	Lending Club
Akinjole et al. (2024)	SVM, MLP, DTree, RF, XGBoost, AdaBoost	AUC: 72.56% $\rightarrow$ 97%, Recall: 66% $\rightarrow$ 97%;	Lending Club
This study	GWE + BlendNet	AUC: $90\%$ , Recall: $81\%$ ; F1-Macro: $75\%$	Lending Club

Table 5: Comparison with recent state-of-the-art studies on Lending Club loan default prediction.

Explore similar work

STRIKE: Additive Feature-Group-Aware Stacking Framework for Credit Default Prediction
Apr 19, 2026Swattik Maiti, Ritik Pratap Singh, Fardina Fathmiul AlamEnsemble Learning Tabular Prediction
Science Academy, University of Maryland, College Park MD, USA · Department of Computer Science, University of Maryland, College Park MD, USA
When Does a Classifier Help an LLM? Classifier-Guided Prompting and Hybrid Classifier-LLM Models for Credit-Default Prediction
Aug 30, 2026Rishi Datta, Lavanya PrahalladLLM Prompting Credit Scoring
Amador Valley High School · Pleasanton, California, USA · Research Spark Hub Inc. +1
Accurate Ensembles, Fragile Narratives: Multi-Scale Stacking and a Fidelity Audit of LLM-Generated Explanations for Credit Risk
Aug 8, 2026Gregorius Reynaldi Pratama, Kuo-Kun TsengFeature Attribution Faithfulness of Language Model Explanations
School of Computer Science and Technology Harbin Institute of Technology, Shenzhen Shenzhen, China

Apr 19, 2026J/K move · Enter open · S save

STRIKE: Additive Feature-Group-Aware Stacking Framework for Credit Default Prediction

Swattik Maiti, Ritik Pratap Singh, Fardina Fathmiul Alam

Science Academy, University of Maryland, College Park MD, USA · Department of Computer Science, University of Maryland, College Park MD, USA

Ensemble Learning Tabular Prediction

Open paper AskPDF arXiv

Credit risk default prediction remains a cornerstone of risk management in the financial industry. The task involves estimating the likelihood that a borrower will fail to meet debt obligations, an objective critical for lending decisions, portfolio optimization, and regulatory compliance. Traditional machine learning models such as logistic regression and tree-based ensembles are widely adopted for their interpretability and strong empirical performance. However, modern credit datasets are high-dimensional, heterogeneous, and noisy, increasing overfitting risk in monolithic models and reducing robustness under distributional shift. We introduce STRIKE (Stacking via Targeted Representations of Isolated Knowledge Extractors), a feature-group-aware stacking framework for structured tabular credit risk data. Rather than training a single monolithic model on the complete dataset, STRIKE partitions the feature space into semantically coherent groups and trains independent learners within each group. This decomposition is motivated by an additive perspective on risk modeling, where distinct feature sources contribute complementary evidence that can be combined through a structured aggregation. The resulting group-specific predictions are integrated through a meta-learner that aggregates signals while maintaining robustness and modularity. We evaluate STRIKE on three real-world datasets spanning corporate bankruptcy and consumer lending scenarios. Across all settings, STRIKE consistently outperforms strong tree-based baselines and conventional stacking approaches in terms of AUC-ROC. Ablation studies confirm that performance gains stem from meaningful feature decomposition rather than increased model complexity. Our findings demonstrate that STRIKE is a stable, scalable, and interpretable framework for credit risk default prediction tasks.

Abstract

Explore similar work

STRIKE: Additive Feature-Group-Aware Stacking Framework for Credit Default Prediction

When Does a Classifier Help an LLM? Classifier-Guided Prompting and Hybrid Classifier-LLM Models for Credit-Default Prediction

Accurate Ensembles, Fragile Narratives: Multi-Scale Stacking and a Fidelity Audit of LLM-Generated Explanations for Credit Risk