A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data
We introduce an estimation framework utilizing a Supervised Variational Autoencoder (SVAE) to address challenges posed by high-dimensional socioeconomic data. Unlike classical linear dimensionality reduction methods, such as PCA and Lasso regression, the proposed SVAE effectively captures complex no...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2026-01-01
|
| Series: | Journal of Economy and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949948825000204 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839634591989628928 |
|---|---|
| author | Pei Xue Tianshun Li |
| author_facet | Pei Xue Tianshun Li |
| author_sort | Pei Xue |
| collection | DOAJ |
| description | We introduce an estimation framework utilizing a Supervised Variational Autoencoder (SVAE) to address challenges posed by high-dimensional socioeconomic data. Unlike classical linear dimensionality reduction methods, such as PCA and Lasso regression, the proposed SVAE effectively captures complex nonlinear interactions through supervised latent representation learning. Empirical analyses using comprehensive cross-country data from the World Bank (196 countries, 1997–2023) demonstrate the SVAE framework’s superior predictive accuracy, interpretability, and robustness in forecasting GDP growth, highlighting its potential for policy evaluation and macroeconomic forecasting. |
| format | Article |
| id | doaj-art-38a6a8d09a8045ceaf6f58f757d3bf5e |
| institution | Matheson Library |
| issn | 2949-9488 |
| language | English |
| publishDate | 2026-01-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Economy and Technology |
| spelling | doaj-art-38a6a8d09a8045ceaf6f58f757d3bf5e2025-07-10T04:35:25ZengKeAi Communications Co., Ltd.Journal of Economy and Technology2949-94882026-01-014919A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic dataPei Xue0Tianshun Li1Tepper School of Business, Carnegie Mellon University, Pittsburgh, PA 15213, USA; Corresponding author.Katz School of Business, University of Pittsburgh, Pittsburgh, PA 15260, USAWe introduce an estimation framework utilizing a Supervised Variational Autoencoder (SVAE) to address challenges posed by high-dimensional socioeconomic data. Unlike classical linear dimensionality reduction methods, such as PCA and Lasso regression, the proposed SVAE effectively captures complex nonlinear interactions through supervised latent representation learning. Empirical analyses using comprehensive cross-country data from the World Bank (196 countries, 1997–2023) demonstrate the SVAE framework’s superior predictive accuracy, interpretability, and robustness in forecasting GDP growth, highlighting its potential for policy evaluation and macroeconomic forecasting.http://www.sciencedirect.com/science/article/pii/S2949948825000204Dimensionality reductionSupervised variational autoencoderNonlinear representation learningHigh-dimensional dataSocioeconomic forecastingPredictive modeling |
| spellingShingle | Pei Xue Tianshun Li A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data Journal of Economy and Technology Dimensionality reduction Supervised variational autoencoder Nonlinear representation learning High-dimensional data Socioeconomic forecasting Predictive modeling |
| title | A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data |
| title_full | A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data |
| title_fullStr | A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data |
| title_full_unstemmed | A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data |
| title_short | A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data |
| title_sort | supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high dimensional socioeconomic data |
| topic | Dimensionality reduction Supervised variational autoencoder Nonlinear representation learning High-dimensional data Socioeconomic forecasting Predictive modeling |
| url | http://www.sciencedirect.com/science/article/pii/S2949948825000204 |
| work_keys_str_mv | AT peixue asupervisedvariationalautoencoderframeworkfordimensionalityreductionandpredictivemodelinginhighdimensionalsocioeconomicdata AT tianshunli asupervisedvariationalautoencoderframeworkfordimensionalityreductionandpredictivemodelinginhighdimensionalsocioeconomicdata AT peixue supervisedvariationalautoencoderframeworkfordimensionalityreductionandpredictivemodelinginhighdimensionalsocioeconomicdata AT tianshunli supervisedvariationalautoencoderframeworkfordimensionalityreductionandpredictivemodelinginhighdimensionalsocioeconomicdata |