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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Economy and Technology Jg. 4; S. 9 - 19
Hauptverfasser: Xue, Pei, Li, Tianshun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 2026
KeAi Communications Co., Ltd
Schlagworte:
ISSN:2949-9488, 2949-9488
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract 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.
AbstractList 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.
Author Xue, Pei
Li, Tianshun
Author_xml – sequence: 1
  givenname: Pei
  orcidid: 0009-0003-8543-8772
  surname: Xue
  fullname: Xue, Pei
  email: peix324@yahoo.com
  organization: Tepper School of Business, Carnegie Mellon University, Pittsburgh, PA 15213, USA
– sequence: 2
  givenname: Tianshun
  surname: Li
  fullname: Li, Tianshun
  email: tianshunli88888@gmail.com
  organization: Katz School of Business, University of Pittsburgh, Pittsburgh, PA 15260, USA
BookMark eNp9kcFq3DAQhkVJoWmaF-hJL2BXsmSvBL2E0LSBQC_JWYyl0UbuWlok74a8Qp66cjaUnHqaGTHfB5r_MzmLKSIhXzlrOePDt6md0C5tx7q-ZUPLGP9AzjstdaOlUmfv-k_kspSJMSYEF1KJc_JyRcthj_kYCjp6hBxgCSnCjsJhSRhtcpipzzDjU8p_qE-ZujBjLK9bYXmmGd3BrhCF6Oi-jqGOR6RzZXchbmmI9DFsH5t3IC3JhoQ2xTQHSx0s8IV89LArePlWL8jDzY_761_N3e-ft9dXd43t2MAb6bh2wFFID1Z2I9vo0Y-bXksGaoTOgra9ZgBu1Ap7iwP3SoxC6nFUnRLigtyevC7BZPY5zJCfTYJgXh9S3hrIS7A7NELBAMoxDYrJqgI_-F75Tb9xYvQ9Vld3ctmcSsno__k4M2s4ZjJrOGYNx7DB1HAq9P0EYf3lMWA2xYZ66nq4vO66FP6H_wWZ2571
Cites_doi 10.1111/rssb.12268
10.1561/2200000056
10.1080/14786440109462720
10.1214/11-EJS631
10.1214/13-AOS1106
10.1016/j.jedc.2022.104530
10.1080/07350015.2015.1102733
10.1080/07350015.2019.1609974
10.1016/S0893-6080(00)00026-5
10.1080/10618600.2023.2256502
10.1198/016214506000000735
10.1111/1468-0262.00273
10.1126/science.1243089
10.1002/wics.101
10.1037/h0071325
10.1016/j.jeconom.2017.08.009
10.1016/bs.hesmac.2016.04.002
10.1093/biomet/90.4.809
10.1080/01621459.2012.734168
10.1016/j.ejor.2016.08.058
10.1609/aaai.v39i19.34204
10.1109/TPAMI.2005.244
10.1257/jep.28.2.3
10.1257/jep.28.2.29
10.1073/pnas.1017031108
10.1111/j.1467-9868.2005.00503.x
10.1101/2024.02.05.578988
10.1016/j.jspi.2009.01.003
10.1016/S0169-7439(01)00155-1
10.1257/aer.104.5.394
10.1038/44565
10.1038/s43586-022-00184-w
10.1080/07350015.2024.2310022
10.1111/j.2517-6161.1996.tb02080.x
10.1257/jep.31.2.87
10.1002/wics.51
10.1093/restud/rdt044
ContentType Journal Article
Copyright 2025 The Authors
Copyright_xml – notice: 2025 The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.ject.2025.06.001
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals (DOAJ)
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2949-9488
EndPage 19
ExternalDocumentID oai_doaj_org_article_38a6a8d09a8045ceaf6f58f757d3bf5e
10_1016_j_ject_2025_06_001
S2949948825000204
GroupedDBID 0R~
6I.
AAFTH
AALRI
AAXUO
AAYWO
ACVFH
ADCNI
ADVLN
AEUPX
AFPUW
AIGII
AITUG
AKBMS
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
FDB
GROUPED_DOAJ
M41
M~E
AAYXX
CITATION
ID FETCH-LOGICAL-c2061-4d19da1e34fac42b079bfb75940a8ba2ca9c590aadb98e5ce61f83b349bb82833
IEDL.DBID DOA
ISSN 2949-9488
IngestDate Fri Oct 03 12:33:05 EDT 2025
Sat Nov 29 07:36:44 EST 2025
Sat Sep 06 17:18:23 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Dimensionality reduction
High-dimensional data
Socioeconomic forecasting
Predictive modeling
Nonlinear representation learning
Supervised variational autoencoder
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2061-4d19da1e34fac42b079bfb75940a8ba2ca9c590aadb98e5ce61f83b349bb82833
ORCID 0009-0003-8543-8772
OpenAccessLink https://doaj.org/article/38a6a8d09a8045ceaf6f58f757d3bf5e
PageCount 11
ParticipantIDs doaj_primary_oai_doaj_org_article_38a6a8d09a8045ceaf6f58f757d3bf5e
crossref_primary_10_1016_j_ject_2025_06_001
elsevier_sciencedirect_doi_10_1016_j_ject_2025_06_001
PublicationCentury 2000
PublicationDate 2026
2026-00-00
2026-01-01
PublicationDateYYYYMMDD 2026-01-01
PublicationDate_xml – year: 2026
  text: 2026
PublicationDecade 2020
PublicationTitle Journal of Economy and Technology
PublicationYear 2026
Publisher Elsevier B.V
KeAi Communications Co., Ltd
Publisher_xml – name: Elsevier B.V
– name: KeAi Communications Co., Ltd
References Ravikumar, P., Wainwright, M.J., Raskutti, G., Yu, B., 2011.High-dimensional covariance estimation by minimizing 1-penalized log-determinant divergence.
Chen, Rohe (bib11) 2024; 33
Greenacre, Groenen, Hastie, d’Enza, Markos, Tuzhilina (bib17) 2022; 2
Cremer, C., Li, X., Duvenaud, D., 2018.Inference suboptimality in variational autoencoders, In: International conference on machine learning, PMLR.1078-1086.
Schockaert, C., Macher, V., Schmitz, A., 2020.Vae-lime: deep generative model based approach for local data-driven model interpretability applied to the ironmaking industry.arXiv preprint arXiv:2007.10256.
Varian (bib43) 2014; 28
Chen, Nordhaus (bib12) 2011; 108
Huang, Kou, Peng (bib21) 2017; 258
Abdi, Williams (bib2) 2010; 2
Lee, Seung (bib25) 1999; 401
Hoyer (bib20) 2004; 5
Qiao, D., Ma, X., Fan, J., 2025.Federated t-sne and umap for distributed data visualization, In: Proceedings of the AAAI Conference on Artificial Intelligence, 20014-20023.
Zou (bib49) 2006; 101
Stock, Watson (bib38) 2016
Rezende, D.J., Mohamed, S., Wierstra, D., 2014.Stochastic backpropagation and approximate inference in deep generative models, In: International conference on machine learning, PMLR.1278-1286.
Pötscher, Schneider (bib32) 2009; 139
Wong, Carter, Kohn (bib46) 2003; 90
Pearson (bib31) 1901; 2
Abdi (bib1) 2010; 2
Belloni, Chernozhukov, Hansen (bib7) 2014; 28
Einav, Levin (bib14) 2014; 346
Papailiopoulos, D., Dimakis, A., Korokythakis, S., 2013.Sparse pca through low-rank approximations, In: International Conference on Machine Learning, PMLR.747-755.
Luo, Zhu (bib27) 2020; 38
Chatterjee, A., Lahiri, S.N., 2013.Rates of convergence of the adaptive lasso estimators to the oracle distribution and higher order refinements by the bootstrap.
Tran, D., Hoffman, M.D., Saurous, R.A., Brevdo, E., Murphy, K., Blei, D.M., 2017.Deep probabilistic programming.arXiv preprint arXiv:1701.03757.
Bernanke, Boivin, Eliasz (bib9) 2005; 120
Belloni, Chernozhukov, Hansen (bib6) 2014; 81
Zimnik, A.J., Ames, K.C., An, X., Driscoll, L., Lara, A.H., Russo, A.A., Susoy, V., Cunningham, J.P., Paninski, L., Churchland, M.M., et al., 2024.Identifying interpretable latent factors with sparse component analysis.bioRxiv.
Wold, Sjöström, Eriksson (bib45) 2001; 58
Refinetti, M., Goldt, S., 2022.The dynamics of representation learning in shallow, non-linear autoencoders, In: International Conference on Machine Learning, PMLR.18499-18519.
Filmer, Pritchett (bib16) 2001; 38
Jin, Lin, Zhang (bib23) 2024; 42
Bai, Ng (bib5) 2002; 70
Louizos, Shalit, Mooij, Sontag, Zemel, Welling (bib26) 2017
Vidal, Ma, Sastry (bib44) 2005; 27
Hyvärinen, Oja (bib22) 2000; 13
Takane (bib40) 2013; 129
Kingma, Welling (bib24) 2019; 12
Mullainathan, Spiess (bib29) 2017; 31
Athey, Imbens, Wager (bib4) 2018; 80
Zou, Hastie (bib50) 2005; 67
Tibshirani (bib41) 1996; 58
Hartford, J., Lewis, G., Leyton-Brown, K., Taddy, M., 2017.Deep iv: A flexible approach for counterfactual prediction, In: International Conference on Machine Learning, PMLR.1414-1423.
Belloni, Chernozhukov, Hansen, Kozbur (bib8) 2016; 34
Hotelling (bib19) 1933; 24
Fan, Xue, Yao (bib15) 2017; 201
Moneta, Pallante (bib28) 2022; 144
Taddy (bib39) 2013; 108
Acemoglu, Autor, Dorn, Hanson, Price (bib3) 2014; 104
Zhou, S., van de Geer, S., Bühlmann, P., 2009.Adaptive lasso for high dimensional regression and gaussian graphical modeling.arXiv preprint arXiv:0903.2515.
10.1016/j.ject.2025.06.001_bib10
Fan (10.1016/j.ject.2025.06.001_bib15) 2017; 201
Hyvärinen (10.1016/j.ject.2025.06.001_bib22) 2000; 13
Stock (10.1016/j.ject.2025.06.001_bib38) 2016
Kingma (10.1016/j.ject.2025.06.001_bib24) 2019; 12
Taddy (10.1016/j.ject.2025.06.001_bib39) 2013; 108
Louizos (10.1016/j.ject.2025.06.001_bib26) 2017
Acemoglu (10.1016/j.ject.2025.06.001_bib3) 2014; 104
10.1016/j.ject.2025.06.001_bib18
Abdi (10.1016/j.ject.2025.06.001_bib2) 2010; 2
10.1016/j.ject.2025.06.001_bib13
Pötscher (10.1016/j.ject.2025.06.001_bib32) 2009; 139
Vidal (10.1016/j.ject.2025.06.001_bib44) 2005; 27
Wong (10.1016/j.ject.2025.06.001_bib46) 2003; 90
Pearson (10.1016/j.ject.2025.06.001_bib31) 1901; 2
Belloni (10.1016/j.ject.2025.06.001_bib6) 2014; 81
Chen (10.1016/j.ject.2025.06.001_bib11) 2024; 33
Jin (10.1016/j.ject.2025.06.001_bib23) 2024; 42
Varian (10.1016/j.ject.2025.06.001_bib43) 2014; 28
Moneta (10.1016/j.ject.2025.06.001_bib28) 2022; 144
Hoyer (10.1016/j.ject.2025.06.001_bib20) 2004; 5
Zou (10.1016/j.ject.2025.06.001_bib50) 2005; 67
10.1016/j.ject.2025.06.001_bib30
Zou (10.1016/j.ject.2025.06.001_bib49) 2006; 101
Hotelling (10.1016/j.ject.2025.06.001_bib19) 1933; 24
Wold (10.1016/j.ject.2025.06.001_bib45) 2001; 58
Filmer (10.1016/j.ject.2025.06.001_bib16) 2001; 38
Luo (10.1016/j.ject.2025.06.001_bib27) 2020; 38
Greenacre (10.1016/j.ject.2025.06.001_bib17) 2022; 2
Bai (10.1016/j.ject.2025.06.001_bib5) 2002; 70
10.1016/j.ject.2025.06.001_bib37
Tibshirani (10.1016/j.ject.2025.06.001_bib41) 1996; 58
10.1016/j.ject.2025.06.001_bib35
Chen (10.1016/j.ject.2025.06.001_bib12) 2011; 108
10.1016/j.ject.2025.06.001_bib36
Belloni (10.1016/j.ject.2025.06.001_bib7) 2014; 28
10.1016/j.ject.2025.06.001_bib33
Bernanke (10.1016/j.ject.2025.06.001_bib9) 2005; 120
Einav (10.1016/j.ject.2025.06.001_bib14) 2014; 346
10.1016/j.ject.2025.06.001_bib34
10.1016/j.ject.2025.06.001_bib42
Takane (10.1016/j.ject.2025.06.001_bib40) 2013; 129
Athey (10.1016/j.ject.2025.06.001_bib4) 2018; 80
Mullainathan (10.1016/j.ject.2025.06.001_bib29) 2017; 31
Lee (10.1016/j.ject.2025.06.001_bib25) 1999; 401
Abdi (10.1016/j.ject.2025.06.001_bib1) 2010; 2
Huang (10.1016/j.ject.2025.06.001_bib21) 2017; 258
10.1016/j.ject.2025.06.001_bib48
10.1016/j.ject.2025.06.001_bib47
Belloni (10.1016/j.ject.2025.06.001_bib8) 2016; 34
References_xml – reference: Zhou, S., van de Geer, S., Bühlmann, P., 2009.Adaptive lasso for high dimensional regression and gaussian graphical modeling.arXiv preprint arXiv:0903.2515.
– volume: 58
  start-page: 109
  year: 2001
  end-page: 130
  ident: bib45
  article-title: Pls-regression: a basic tool of chemometrics
  publication-title: Chemom. Intell. Lab. Syst.
– volume: 139
  start-page: 2775
  year: 2009
  end-page: 2790
  ident: bib32
  article-title: On the distribution of the adaptive lasso estimator
  publication-title: J. Stat. Plan. Inference
– volume: 38
  start-page: 115
  year: 2001
  end-page: 132
  ident: bib16
  article-title: Estimating wealth effects without expenditure data—or tears: an application to educational enrollments in states of india
  publication-title: Demography
– reference: Zimnik, A.J., Ames, K.C., An, X., Driscoll, L., Lara, A.H., Russo, A.A., Susoy, V., Cunningham, J.P., Paninski, L., Churchland, M.M., et al., 2024.Identifying interpretable latent factors with sparse component analysis.bioRxiv.
– volume: 101
  start-page: 1418
  year: 2006
  end-page: 1429
  ident: bib49
  article-title: The adaptive lasso and its oracle properties
  publication-title: J. Am. Stat. Assoc.
– volume: 120
  start-page: 387
  year: 2005
  end-page: 422
  ident: bib9
  article-title: Measuring the effects of monetary policy: a factor-augmented vector autoregressive (favar) approach
  publication-title: Q. J. Econ.
– volume: 104
  start-page: 394
  year: 2014
  end-page: 399
  ident: bib3
  article-title: Return of the solow paradox? it, productivity, and employment in us manufacturing
  publication-title: Am. Econ. Rev.
– volume: 70
  start-page: 191
  year: 2002
  end-page: 221
  ident: bib5
  article-title: Determining the number of factors in approximate factor models
  publication-title: Econometrica
– volume: 2
  start-page: 559
  year: 1901
  end-page: 572
  ident: bib31
  article-title: Liii. on lines and planes of closest fit to systems of points in space
  publication-title: Lond. Edinb. Dublin Philos. Mag. J. Sci.
– reference: Tran, D., Hoffman, M.D., Saurous, R.A., Brevdo, E., Murphy, K., Blei, D.M., 2017.Deep probabilistic programming.arXiv preprint arXiv:1701.03757.
– volume: 27
  start-page: 1945
  year: 2005
  end-page: 1959
  ident: bib44
  article-title: Generalized principal component analysis (gpca)
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 2
  start-page: 97
  year: 2010
  end-page: 106
  ident: bib1
  article-title: Partial least squares regression and projection on latent structure regression (pls regression)
  publication-title: Wiley Interdiscip. Rev. Comput. Stat.
– volume: 90
  start-page: 809
  year: 2003
  end-page: 830
  ident: bib46
  article-title: Efficient estimation of covariance selection models
  publication-title: Biometrika
– volume: 129
  start-page: 129
  year: 2013
  ident: bib40
  article-title: Constrained principal component analysis and related techniques
  publication-title: Monogr. Stat. Appl. Probab.
– reference: Ravikumar, P., Wainwright, M.J., Raskutti, G., Yu, B., 2011.High-dimensional covariance estimation by minimizing 1-penalized log-determinant divergence.
– volume: 33
  start-page: 421
  year: 2024
  end-page: 434
  ident: bib11
  article-title: A new basis for sparse principal component analysis
  publication-title: J. Comput. Graph. Stat.
– volume: 346
  year: 2014
  ident: bib14
  article-title: Economics in the age of big data
  publication-title: Science
– volume: 108
  start-page: 755
  year: 2013
  end-page: 770
  ident: bib39
  article-title: Multinomial inverse regression for text analysis
  publication-title: J. Am. Stat. Assoc.
– volume: 58
  start-page: 267
  year: 1996
  end-page: 288
  ident: bib41
  article-title: Regression shrinkage and selection via the lasso
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
– reference: Rezende, D.J., Mohamed, S., Wierstra, D., 2014.Stochastic backpropagation and approximate inference in deep generative models, In: International conference on machine learning, PMLR.1278-1286.
– volume: 31
  start-page: 87
  year: 2017
  end-page: 106
  ident: bib29
  article-title: Machine learning: an applied econometric approach
  publication-title: J. Econ. Perspect.
– volume: 34
  start-page: 590
  year: 2016
  end-page: 605
  ident: bib8
  article-title: Inference in high-dimensional panel models with an application to gun control
  publication-title: J. Bus. Econ. Stat.
– volume: 201
  start-page: 292
  year: 2017
  end-page: 306
  ident: bib15
  article-title: Sufficient forecasting using factor models
  publication-title: J. Econ.
– reference: Cremer, C., Li, X., Duvenaud, D., 2018.Inference suboptimality in variational autoencoders, In: International conference on machine learning, PMLR.1078-1086.
– volume: 67
  start-page: 301
  year: 2005
  end-page: 320
  ident: bib50
  article-title: Regularization and variable selection via the elastic net
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
– volume: 2
  start-page: 100
  year: 2022
  ident: bib17
  article-title: Principal component analysis
  publication-title: Nat. Rev. Methods Prim.
– volume: 144
  year: 2022
  ident: bib28
  article-title: Identification of structural var models via independent component analysis: A performance evaluation study
  publication-title: J. Econ. Dyn. Control
– reference: Refinetti, M., Goldt, S., 2022.The dynamics of representation learning in shallow, non-linear autoencoders, In: International Conference on Machine Learning, PMLR.18499-18519.
– volume: 24
  start-page: 417
  year: 1933
  ident: bib19
  article-title: Analysis of a complex of statistical variables into principal components
  publication-title: J. Educ. Psychol.
– volume: 38
  start-page: 888
  year: 2020
  end-page: 900
  ident: bib27
  article-title: Matching using sufficient dimension reduction for causal inference
  publication-title: J. Bus. Econ. Stat.
– reference: Papailiopoulos, D., Dimakis, A., Korokythakis, S., 2013.Sparse pca through low-rank approximations, In: International Conference on Machine Learning, PMLR.747-755.
– start-page: 415
  year: 2016
  end-page: 525
  ident: bib38
  article-title: Dynamic factor models, factor-augmented vector autoregressions, and structural vector autoregressions in macroeconomics
  publication-title: Handbook of macroeconomics
– volume: 28
  start-page: 3
  year: 2014
  end-page: 28
  ident: bib43
  article-title: Big data: New tricks for econometrics
  publication-title: J. Econ. Perspect.
– volume: 108
  start-page: 8589
  year: 2011
  end-page: 8594
  ident: bib12
  article-title: Using luminosity data as a proxy for economic statistics
  publication-title: Proc. Natl. Acad. Sci.
– reference: Schockaert, C., Macher, V., Schmitz, A., 2020.Vae-lime: deep generative model based approach for local data-driven model interpretability applied to the ironmaking industry.arXiv preprint arXiv:2007.10256.
– reference: Qiao, D., Ma, X., Fan, J., 2025.Federated t-sne and umap for distributed data visualization, In: Proceedings of the AAAI Conference on Artificial Intelligence, 20014-20023.
– start-page: 30
  year: 2017
  ident: bib26
  article-title: Causal effect inference with deep latent-variable models
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 258
  start-page: 692
  year: 2017
  end-page: 702
  ident: bib21
  article-title: Nonlinear manifold learning for early warnings in financial markets
  publication-title: Eur. J. Oper. Res.
– reference: Chatterjee, A., Lahiri, S.N., 2013.Rates of convergence of the adaptive lasso estimators to the oracle distribution and higher order refinements by the bootstrap.
– volume: 5
  start-page: 1457
  year: 2004
  end-page: 1469
  ident: bib20
  article-title: Non-negative matrix factorization with sparseness constraints
  publication-title: J. Mach. Learn. Res.
– volume: 401
  start-page: 788
  year: 1999
  end-page: 791
  ident: bib25
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: nature
– volume: 12
  start-page: 307
  year: 2019
  end-page: 392
  ident: bib24
  article-title: An introduction to variational autoencoders
  publication-title: Found. Trends® Mach. Learn.
– reference: Hartford, J., Lewis, G., Leyton-Brown, K., Taddy, M., 2017.Deep iv: A flexible approach for counterfactual prediction, In: International Conference on Machine Learning, PMLR.1414-1423.
– volume: 81
  start-page: 608
  year: 2014
  end-page: 650
  ident: bib6
  article-title: Inference on treatment effects after selection among high-dimensional controls
  publication-title: Rev. Econ. Stud.
– volume: 13
  start-page: 411
  year: 2000
  end-page: 430
  ident: bib22
  article-title: Independent component analysis: algorithms and applications
  publication-title: Neural Netw.
– volume: 80
  start-page: 597
  year: 2018
  end-page: 623
  ident: bib4
  article-title: Approximate residual balancing: debiased inference of average treatment effects in high dimensions
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
– volume: 2
  start-page: 433
  year: 2010
  end-page: 459
  ident: bib2
  article-title: Principal component analysis
  publication-title: Wiley Interdiscip. Rev. Comput. Stat.
– volume: 28
  start-page: 29
  year: 2014
  end-page: 50
  ident: bib7
  article-title: High-dimensional methods and inference on structural and treatment effects
  publication-title: J. Econ. Perspect.
– volume: 42
  start-page: 1318
  year: 2024
  end-page: 1330
  ident: bib23
  article-title: Identification and auto-debiased machine learning for outcome-conditioned average structural derivatives
  publication-title: J. Bus. Econ. Stat.
– volume: 80
  start-page: 597
  year: 2018
  ident: 10.1016/j.ject.2025.06.001_bib4
  article-title: Approximate residual balancing: debiased inference of average treatment effects in high dimensions
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
  doi: 10.1111/rssb.12268
– ident: 10.1016/j.ject.2025.06.001_bib42
– ident: 10.1016/j.ject.2025.06.001_bib13
– start-page: 30
  year: 2017
  ident: 10.1016/j.ject.2025.06.001_bib26
  article-title: Causal effect inference with deep latent-variable models
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 12
  start-page: 307
  year: 2019
  ident: 10.1016/j.ject.2025.06.001_bib24
  article-title: An introduction to variational autoencoders
  publication-title: Found. Trends® Mach. Learn.
  doi: 10.1561/2200000056
– volume: 2
  start-page: 559
  year: 1901
  ident: 10.1016/j.ject.2025.06.001_bib31
  article-title: Liii. on lines and planes of closest fit to systems of points in space
  publication-title: Lond. Edinb. Dublin Philos. Mag. J. Sci.
  doi: 10.1080/14786440109462720
– volume: 120
  start-page: 387
  year: 2005
  ident: 10.1016/j.ject.2025.06.001_bib9
  article-title: Measuring the effects of monetary policy: a factor-augmented vector autoregressive (favar) approach
  publication-title: Q. J. Econ.
– ident: 10.1016/j.ject.2025.06.001_bib34
  doi: 10.1214/11-EJS631
– ident: 10.1016/j.ject.2025.06.001_bib36
– ident: 10.1016/j.ject.2025.06.001_bib10
  doi: 10.1214/13-AOS1106
– volume: 144
  year: 2022
  ident: 10.1016/j.ject.2025.06.001_bib28
  article-title: Identification of structural var models via independent component analysis: A performance evaluation study
  publication-title: J. Econ. Dyn. Control
  doi: 10.1016/j.jedc.2022.104530
– ident: 10.1016/j.ject.2025.06.001_bib47
– ident: 10.1016/j.ject.2025.06.001_bib30
– volume: 34
  start-page: 590
  year: 2016
  ident: 10.1016/j.ject.2025.06.001_bib8
  article-title: Inference in high-dimensional panel models with an application to gun control
  publication-title: J. Bus. Econ. Stat.
  doi: 10.1080/07350015.2015.1102733
– volume: 38
  start-page: 888
  year: 2020
  ident: 10.1016/j.ject.2025.06.001_bib27
  article-title: Matching using sufficient dimension reduction for causal inference
  publication-title: J. Bus. Econ. Stat.
  doi: 10.1080/07350015.2019.1609974
– volume: 38
  start-page: 115
  year: 2001
  ident: 10.1016/j.ject.2025.06.001_bib16
  article-title: Estimating wealth effects without expenditure data—or tears: an application to educational enrollments in states of india
  publication-title: Demography
– volume: 13
  start-page: 411
  year: 2000
  ident: 10.1016/j.ject.2025.06.001_bib22
  article-title: Independent component analysis: algorithms and applications
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(00)00026-5
– ident: 10.1016/j.ject.2025.06.001_bib37
– volume: 33
  start-page: 421
  year: 2024
  ident: 10.1016/j.ject.2025.06.001_bib11
  article-title: A new basis for sparse principal component analysis
  publication-title: J. Comput. Graph. Stat.
  doi: 10.1080/10618600.2023.2256502
– volume: 101
  start-page: 1418
  year: 2006
  ident: 10.1016/j.ject.2025.06.001_bib49
  article-title: The adaptive lasso and its oracle properties
  publication-title: J. Am. Stat. Assoc.
  doi: 10.1198/016214506000000735
– volume: 70
  start-page: 191
  year: 2002
  ident: 10.1016/j.ject.2025.06.001_bib5
  article-title: Determining the number of factors in approximate factor models
  publication-title: Econometrica
  doi: 10.1111/1468-0262.00273
– volume: 346
  year: 2014
  ident: 10.1016/j.ject.2025.06.001_bib14
  article-title: Economics in the age of big data
  publication-title: Science
  doi: 10.1126/science.1243089
– volume: 2
  start-page: 433
  year: 2010
  ident: 10.1016/j.ject.2025.06.001_bib2
  article-title: Principal component analysis
  publication-title: Wiley Interdiscip. Rev. Comput. Stat.
  doi: 10.1002/wics.101
– volume: 24
  start-page: 417
  year: 1933
  ident: 10.1016/j.ject.2025.06.001_bib19
  article-title: Analysis of a complex of statistical variables into principal components
  publication-title: J. Educ. Psychol.
  doi: 10.1037/h0071325
– volume: 201
  start-page: 292
  year: 2017
  ident: 10.1016/j.ject.2025.06.001_bib15
  article-title: Sufficient forecasting using factor models
  publication-title: J. Econ.
  doi: 10.1016/j.jeconom.2017.08.009
– start-page: 415
  year: 2016
  ident: 10.1016/j.ject.2025.06.001_bib38
  article-title: Dynamic factor models, factor-augmented vector autoregressions, and structural vector autoregressions in macroeconomics
  doi: 10.1016/bs.hesmac.2016.04.002
– volume: 90
  start-page: 809
  year: 2003
  ident: 10.1016/j.ject.2025.06.001_bib46
  article-title: Efficient estimation of covariance selection models
  publication-title: Biometrika
  doi: 10.1093/biomet/90.4.809
– volume: 108
  start-page: 755
  year: 2013
  ident: 10.1016/j.ject.2025.06.001_bib39
  article-title: Multinomial inverse regression for text analysis
  publication-title: J. Am. Stat. Assoc.
  doi: 10.1080/01621459.2012.734168
– volume: 258
  start-page: 692
  year: 2017
  ident: 10.1016/j.ject.2025.06.001_bib21
  article-title: Nonlinear manifold learning for early warnings in financial markets
  publication-title: Eur. J. Oper. Res.
  doi: 10.1016/j.ejor.2016.08.058
– ident: 10.1016/j.ject.2025.06.001_bib33
  doi: 10.1609/aaai.v39i19.34204
– volume: 27
  start-page: 1945
  year: 2005
  ident: 10.1016/j.ject.2025.06.001_bib44
  article-title: Generalized principal component analysis (gpca)
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2005.244
– volume: 28
  start-page: 3
  year: 2014
  ident: 10.1016/j.ject.2025.06.001_bib43
  article-title: Big data: New tricks for econometrics
  publication-title: J. Econ. Perspect.
  doi: 10.1257/jep.28.2.3
– volume: 28
  start-page: 29
  year: 2014
  ident: 10.1016/j.ject.2025.06.001_bib7
  article-title: High-dimensional methods and inference on structural and treatment effects
  publication-title: J. Econ. Perspect.
  doi: 10.1257/jep.28.2.29
– volume: 108
  start-page: 8589
  year: 2011
  ident: 10.1016/j.ject.2025.06.001_bib12
  article-title: Using luminosity data as a proxy for economic statistics
  publication-title: Proc. Natl. Acad. Sci.
  doi: 10.1073/pnas.1017031108
– volume: 67
  start-page: 301
  year: 2005
  ident: 10.1016/j.ject.2025.06.001_bib50
  article-title: Regularization and variable selection via the elastic net
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
  doi: 10.1111/j.1467-9868.2005.00503.x
– ident: 10.1016/j.ject.2025.06.001_bib48
  doi: 10.1101/2024.02.05.578988
– ident: 10.1016/j.ject.2025.06.001_bib18
– volume: 129
  start-page: 129
  year: 2013
  ident: 10.1016/j.ject.2025.06.001_bib40
  article-title: Constrained principal component analysis and related techniques
  publication-title: Monogr. Stat. Appl. Probab.
– volume: 139
  start-page: 2775
  year: 2009
  ident: 10.1016/j.ject.2025.06.001_bib32
  article-title: On the distribution of the adaptive lasso estimator
  publication-title: J. Stat. Plan. Inference
  doi: 10.1016/j.jspi.2009.01.003
– volume: 58
  start-page: 109
  year: 2001
  ident: 10.1016/j.ject.2025.06.001_bib45
  article-title: Pls-regression: a basic tool of chemometrics
  publication-title: Chemom. Intell. Lab. Syst.
  doi: 10.1016/S0169-7439(01)00155-1
– volume: 104
  start-page: 394
  year: 2014
  ident: 10.1016/j.ject.2025.06.001_bib3
  article-title: Return of the solow paradox? it, productivity, and employment in us manufacturing
  publication-title: Am. Econ. Rev.
  doi: 10.1257/aer.104.5.394
– volume: 401
  start-page: 788
  year: 1999
  ident: 10.1016/j.ject.2025.06.001_bib25
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: nature
  doi: 10.1038/44565
– volume: 2
  start-page: 100
  year: 2022
  ident: 10.1016/j.ject.2025.06.001_bib17
  article-title: Principal component analysis
  publication-title: Nat. Rev. Methods Prim.
  doi: 10.1038/s43586-022-00184-w
– volume: 5
  start-page: 1457
  year: 2004
  ident: 10.1016/j.ject.2025.06.001_bib20
  article-title: Non-negative matrix factorization with sparseness constraints
  publication-title: J. Mach. Learn. Res.
– volume: 42
  start-page: 1318
  year: 2024
  ident: 10.1016/j.ject.2025.06.001_bib23
  article-title: Identification and auto-debiased machine learning for outcome-conditioned average structural derivatives
  publication-title: J. Bus. Econ. Stat.
  doi: 10.1080/07350015.2024.2310022
– ident: 10.1016/j.ject.2025.06.001_bib35
– volume: 58
  start-page: 267
  year: 1996
  ident: 10.1016/j.ject.2025.06.001_bib41
  article-title: Regression shrinkage and selection via the lasso
  publication-title: J. R. Stat. Soc. Ser. B Stat. Methodol.
  doi: 10.1111/j.2517-6161.1996.tb02080.x
– volume: 31
  start-page: 87
  year: 2017
  ident: 10.1016/j.ject.2025.06.001_bib29
  article-title: Machine learning: an applied econometric approach
  publication-title: J. Econ. Perspect.
  doi: 10.1257/jep.31.2.87
– volume: 2
  start-page: 97
  year: 2010
  ident: 10.1016/j.ject.2025.06.001_bib1
  article-title: Partial least squares regression and projection on latent structure regression (pls regression)
  publication-title: Wiley Interdiscip. Rev. Comput. Stat.
  doi: 10.1002/wics.51
– volume: 81
  start-page: 608
  year: 2014
  ident: 10.1016/j.ject.2025.06.001_bib6
  article-title: Inference on treatment effects after selection among high-dimensional controls
  publication-title: Rev. Econ. Stud.
  doi: 10.1093/restud/rdt044
SSID ssj0003313483
Score 2.313403
Snippet We introduce an estimation framework utilizing a Supervised Variational Autoencoder (SVAE) to address challenges posed by high-dimensional socioeconomic data....
SourceID doaj
crossref
elsevier
SourceType Open Website
Index Database
Publisher
StartPage 9
SubjectTerms Dimensionality reduction
High-dimensional data
Nonlinear representation learning
Predictive modeling
Socioeconomic forecasting
Supervised variational autoencoder
Title A supervised variational autoencoder framework for dimensionality reduction and predictive modeling in high-dimensional socioeconomic data
URI https://dx.doi.org/10.1016/j.ject.2025.06.001
https://doaj.org/article/38a6a8d09a8045ceaf6f58f757d3bf5e
Volume 4
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Directory of Open Access Journals (DOAJ)
  customDbUrl:
  eissn: 2949-9488
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003313483
  issn: 2949-9488
  databaseCode: DOA
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2949-9488
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003313483
  issn: 2949-9488
  databaseCode: M~E
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxcCCQIAoL3lgQ4EkdhJ7LKgVA1QMIHWL_JTKkFbpY-QH8Ku5ixMUFlhYMkSxHd3Zd9_Zd58Juc6NRzceR95KCFC0wWJlm8K6yk3BvQGf0RQKPxXTqZjN5Evvqi_MCQv0wEFwd0yoXAkbSyUAfRinfO4z4YussEz7zKH1BdTTC6bQBjOWMC5YWyUTErpwXwMCwjS7DQcQPzxRQ9jfc0g9JzM5IPstOqSj8FeHZMdVR-RzRFebJa7plbN0C8Ftu4FH1Wa9QCJK62rquywrCjCUWiTtD4QbALNpjQSt2IiqytJljaczaOdocxEOeC86rygyF0e9hhQVt3Bt5TLFXNJj8jYZvz48Ru0VCpFJwVNH3CbSqsQx7pXhqY4Lqb0uMsljJbRKjZImk7FSVkvhQLx54gXTjEutIRZj7IQMqkXlTgk1CrAeS3LMnuLaZgKspEqZKRLjFQRdQ3LTibNcBqaMskshey9R-CUKvwx5dENyjxL__hJZrpsXoPuy1X35l-6HJOv0VbaAIQAB6Gr-y-Bn_zH4OdmDLtvtmAsyWNcbd0l2zXY9X9VXzXSE5_PH-At-wevL
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+supervised+variational+autoencoder+framework+for+dimensionality+reduction+and+predictive+modeling+in+high-dimensional+socioeconomic+data&rft.jtitle=Journal+of+Economy+and+Technology&rft.au=Xue%2C+Pei&rft.au=Li%2C+Tianshun&rft.date=2026&rft.issn=2949-9488&rft.eissn=2949-9488&rft.volume=4&rft.spage=9&rft.epage=19&rft_id=info:doi/10.1016%2Fj.ject.2025.06.001&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ject_2025_06_001
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2949-9488&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2949-9488&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2949-9488&client=summon