Enterprise intelligent financial condition evaluation based on stacking ensemble model

The traditional methods for intelligent evaluation of the financial state of enterprises demonstrate low stability and poor cross-scenario adaptability of their results. This study proposes a new method for evaluating the financial state of enterprises based on the Stacked Generalization ensemble. It optimizes hyperparameters of the model and performs effective selection of financial features. It combines the Attention Mechanism with Weighted Fusion to achieve dynamic adaptation of heterogeneous financial data. Then it uses hierarchical fusion modeling based on Stacked Generalization to capture the internal relationships among financial indicators. In this way, it achieves efficient evaluation of enterprise financial conditions. In experiments, the model achieves an evaluation accuracy of 98.15% and a misclassification rate of 1.08%. Under cross-industry heterogeneous data scenarios, the scenario adaptation accuracy reaches 97.89%, and the evaluation consistency score reaches 98.23%. In enterprise investment and financing due diligence scenarios, the financial evaluation accuracy reaches 98.65%, and the financial risk tracing ability reaches 0.965. In the identification of four types of financial risks, the model achieves accuracies of 95.38%, 95.12%, 96.87%, and 96.63%. These results indicate that this method outperforms the comparative approaches in terms of evaluation precision, scenario adaptation, and risk recognition capability.

Authors

Institutions

Publication Details

Journal
Discover Computing
Published
2026-11-17
DOI
https://doi.org/10.1007/s10791-026-10638-4
Primary Topic
Financial Distress and Bankruptcy Prediction
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Enterprise intelligent financial condition evaluation based on stacking ensemble model

Lan Shu, Jiao Shu, Qingqing Duan
Discover Computing
Financial Distress and Bankruptcy Prediction
article

Enterprise intelligent financial condition evaluation based on stacking ensemble model

Lan Shu, Jiao Shu, Qingqing Duan
article en

Abstract

The traditional methods for intelligent evaluation of the financial state of enterprises demonstrate low stability and poor cross-scenario adaptability of their results. This study proposes a new method for evaluating the financial state of enterprises based on the Stacked Generalization ensemble. It optimizes hyperparameters of the model and performs effective selection of financial features. It combines the Attention Mechanism with Weighted Fusion to achieve dynamic adaptation of heterogeneous financial data. Then it uses hierarchical fusion modeling based on Stacked Generalization to capture the internal relationships among financial indicators. In this way, it achieves efficient evaluation of enterprise financial conditions. In experiments, the model achieves an evaluation accuracy of 98.15% and a misclassification rate of 1.08%. Under cross-industry heterogeneous data scenarios, the scenario adaptation accuracy reaches 97.89%, and the evaluation consistency score reaches 98.23%. In enterprise investment and financing due diligence scenarios, the financial evaluation accuracy reaches 98.65%, and the financial risk tracing ability reaches 0.965. In the identification of four types of financial risks, the model achieves accuracies of 95.38%, 95.12%, 96.87%, and 96.63%. These results indicate that this method outperforms the comparative approaches in terms of evaluation precision, scenario adaptation, and risk recognition capability.

Discover ComputingVol. 29(1)
Guangdong University Of Finances and Economics (CN), Hunan University of Technology (CN)
Financial Distress and Bankruptcy Prediction
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon