Author(s)

YiFan Fan

Affiliation(s)

Business school of Nanjing Normal University, Nanjing Normal University, Nanjing, 210023, Jiangsu, China.

Corresponding Author

YiFan Fan

ABSTRACT

In highly complex and dynamically changing decision-making environments, constructing predictive models with strong generalization capabilities, robustness, and high interpretability based on large-scale heterogeneous data has become an important research topic in the field of intelligent modeling. Targeting the deficiencies of traditional models in modeling nonlinear relationships, capturing high-dimensional feature interactions, and outputting consistent results, this paper proposes an end-to-end advanced predictive modeling framework. This framework integrates hierarchical model stacking ensemble and adaptive hyperparameter optimization techniques, enhancing predictive accuracy through knowledge collaboration among models and effectively suppressing overfitting risks. In model result evaluation, multiple metrics such as ROC-AUC, KS index, Precision, Recall, and F1-Score are comprehensively introduced to ensure the robust performance of the model under complex and uncertain conditions. Meanwhile, through Permutation Importance, Partial Dependence Plot (PDP), and the SHAP interpretability framework, transparent explanations at both the global and local levels of the model are realized, effectively revealing the nonlinear driving effects and interaction mechanisms of high-impact features. To address the consistency and comparability of predictive results in cross-scenario decision-making, this paper further constructs a standardized score mapping mechanism based on log-odds transformation, mapping model outputs to a continuous and interpretable score range, enhancing the intuitive interpretability and system adaptability of model results. Comparative experimental results verify the comprehensive advantages of the proposed framework in terms of predictive accuracy, interpretability, and output standardization, providing a complete and scalable technical paradigm for intelligent decision-making in complex systems.

KEYWORDS

Hierarchical model integration; Adaptive hyperparameter optimization; Standardized score mapping; SHAP interpretability framework; Robust prediction

CITE THIS PAPER

YiFan Fan. Optimization of model integration and quantitative score mapping for complex decision - making environments. World Journal of Information Technology. 2025, 3(4): 23-33. DOI: https://doi.org/10.61784/wjit3050.

REFERENCES

[1] Grunewald E, Barrenetxea J, Giesa N, et al. Coding Clinic: A Multidisciplinary Approach Supporting Early-Stage Medical Data Science Research. Studies in Health Technology and Informatics, 2025, 327: 1086-1087.

[2] Kang G, Tan M, Zou X, et al. An Intelligent Decision-Making for Electromagnetic Spectrum Allocation Method Based on the Monte Carlo Counterfactual Regret Minimization Algorithm in Complex Environments. Atmosphere, 2025, 16(3): 345.

[3] Hauschild M Z, McKone T E, Karsten N A, et al. Risk and Sustainability: Trade-offs and Synergies for Robust Decision Making. Environmental Sciences Europe, 2022, 34(1).

[4] Chen Y, Wang J, Li R, et al. Particulate Matter 2.5 Concentration Prediction System Based on Uncertainty Analysis and Multi-Model Integration. The Science of the Total Environment, 2024, 958: 177924.

[5] Upreti B B, Samui S, Dey S R. Electrochemical Energy Storage Enhanced by Intermediate Layer Stacking of Heteroatom-Enriched Covalent Organic Polymers in Exfoliated Graphene. Nanoscale, 2025.

[6] Philip S, Marakkath N. Compressive Strength Prediction and Feature Analysis for GGBS-Based Geopolymer Concrete Using Optimized XGBoost and SHAP: A Comparative Study of Optimization Algorithms and Experimental Validation. Journal of Building Engineering, 2025, 108: 112879.

[7] Zhang T, Li Z, Zhang Z, et al. Machine Learning-Based Energy Consumption Models for Rural Housing Envelope Retrofits Incorporating Uncertainty: A Case Study in Jiaxian, China. Case Studies in Thermal Engineering, 2025, 72: 106253.

[8] Johnston H, Nair N, Du D. Estimating Calibrated Risks Using Focal Loss and Gradient-Boosted Trees for Clinical Risk Prediction. Electronics, 2025, 14(9): 1838.

[9] René P, Marja F, Martin A S, et al. Random Forest and Gradient Boosted Trees for Patient Individualized Contrast Agent Dose Reduction in CT Angiography. Studies in Health Technology and Informatics, 2023, 302: 952-956.

[10] Sun X, Wang Y, Cheng Z, et al. Deep Learning Framework Incorporating Simultaneous Optimization and Training for Concurrent Estimation and Prediction of Battery State of Health. Journal of Power Sources, 2025, 644: 237027.

[11] Xin X, Maokun L, Tingting X. Epilepsy Seizures Prediction Based on Nonlinear Features of EEG Signal and Gradient Boosting Decision Tree. International Journal of Environmental Research and Public Health, 2022, 19(18): 11326.

[12] Garitta C, Grassi L. Predicting Break-Even in FinTech Startups as a Signal for Success. Finance Research Letters, 2025, 74: 106735.