A Deep Learning-Based Approach for Relative Poverty Identification and Classification Prediction

Tianqi Ding

doi:10.62051/ijepes.v4n1.05

Authors

Tianqi Ding

DOI:

https://doi.org/10.62051/ijepes.v4n1.05

Keywords:

DNN Model, SHAP Model, Relative Poverty Classification and Prediction, Feature Selection

Abstract

By predicting and classifying relative poverty, we can spot and tell the difference between potentially impoverished groups early on. This allows for early intervention and efficient resource allocation, aiding long - term poverty governance. Given the lack of algorithmic research in relative poverty identification using multi - year data, this paper proposes the RP - DCSA model. It blends deep learning (DNN) with the interpretable SHapley Additive exPlanation (SHAP) model. The 2020 China Family Panel Studies (CFPS) survey data form the research base. Spearman correlation coefficients are applied for feature selection to eliminate redundant ones. Next, the DNN - based RP - DCSA model is built and compared experimentally with LR, RF, etc. Finally, SHAP is used for interpretable analysis to identify key features affecting relative poverty classification and assess their impact on results. The RP-DCSA model achieves an 89.55% classification accuracy on the CFPS2020 dataset, outperforming other algorithms in various indicators.

References

[1] Tan,X.W.,Dong,M.,Ou.Y.X.,et al.(2024).New Advances in Anti-Poverty Research in the New Era: A Summary of the International Seminar on "Innovations in Anti-Poverty Theory". Chinese Rural Economy, 06, 173-184.

[2] Zhou,Z.H.,&Li,X.Y.(2024).Analysis of the Spirit of Poverty Alleviation and Common Prosperity in the New Era. Shanghai Economic Research, 424(01), 5-14.

[3] Chen,W.Q.,&Yang,Z.L.(2024). Research on the Modernization Path of Governance of Relative Poverty in Chinese Small-Scale Agriculture. Agricultural Economics,05, 102-104.

[4] Qiu,H.,&Du,Z.L.(2024). Multi-dimensional Dilemmas and Mechanism Construction of Governance of Relative Poverty. Academic Exchange,02, 143-157.

[5] Luo,Y.Q.,Liu,M.P.,Chen,S.W.,et al.(2025).Charging Load Forecasting and Optimal Scheduling Model Based on Deep Neural Network. Electronic Design Engineering,33(08),92 - 95.DOI:10.14022/j.issn1674 - 6236.2025.08.019.

[6] Qin,X.Y.,Luo,D.,Ye,C.(2025).Analysis of Factors Affecting Average Hospitalization Days Based on Deep Neural Network. Modern Hospital,25(03),388 - 392.

[7] Luo,H.,Li,P.(2025).Establishment of Enhanced CT Image Kidney Segmentation Model Based on Deep Neural Network. Chongqing Medical Journal,54(03),630 - 634.

[8] Li, Z. (2022). Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost. Computers, Environment and Urban Systems, 96, 101845.

[9] Feng, D.C., Wang, W.J., Mangalathu, S., et al. (2021). Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls. Journal of Structural Engineering, 147(11), 04021173.

[10] Pan,R.P.,Yang,H.,Xin,B.X.,et al.(2025).Monitoring and Early Warning Method for Feeder Power Failure Risk Based on Spearman Correlation Coefficient. China New Technologies and New Products,(05),137 - 139.DOI:10.13612/j.cnki.cntp.2025.05.026.