An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia

Addressing unemployment is essential for formulating effective public policies. In particular, socioeconomic and monetary variables serve as essential indicators for anticipating labor market trends, given their strong influence on employment dynamics and economic stability. However, effective unemp...

Full description

Saved in:
Bibliographic Details
Main Authors: Diego Armando Pérez-Rosero, Diego Alejandro Manrique-Cabezas, Jennifer Carolina Triana-Martinez, Andrés Marino Álvarez-Meza, German Castellanos-Dominguez
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Computation
Subjects:
Online Access:https://www.mdpi.com/2079-3197/13/5/116
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257875182551040
author Diego Armando Pérez-Rosero
Diego Alejandro Manrique-Cabezas
Jennifer Carolina Triana-Martinez
Andrés Marino Álvarez-Meza
German Castellanos-Dominguez
author_facet Diego Armando Pérez-Rosero
Diego Alejandro Manrique-Cabezas
Jennifer Carolina Triana-Martinez
Andrés Marino Álvarez-Meza
German Castellanos-Dominguez
author_sort Diego Armando Pérez-Rosero
collection DOAJ
description Addressing unemployment is essential for formulating effective public policies. In particular, socioeconomic and monetary variables serve as essential indicators for anticipating labor market trends, given their strong influence on employment dynamics and economic stability. However, effective unemployment rate prediction requires addressing the non-stationary and non-linear characteristics of labor data. Equally important is the preservation of interpretability in both samples and features to ensure that forecasts can meaningfully inform public decision-making. Here, we provide an explainable framework integrating unsupervised and supervised machine learning to enhance unemployment rate prediction and interpretability. Our approach is threefold: (i) we gather a dataset for Colombian unemployment rate prediction including monetary and socioeconomic variables. (ii) Then, we used a Local Biplot technique from the widely recognized Uniform Manifold Approximation and Projection (UMAP) method along with local affine transformations as an unsupervised representation of non-stationary and non-linear data patterns in a simplified and comprehensible manner. (iii) A Gaussian Processes regressor with kernel-based feature relevance analysis is coupled as a supervised counterpart for both unemployment rate prediction and input feature importance analysis. We demonstrated the effectiveness of our proposed approach through a series of experiments conducted on our customized database focused on unemployment indicators in Colombia. Furthermore, we carried out a comparative analysis between traditional statistical techniques and modern machine learning methods. The results revealed that our framework significantly enhances both clustering and predictive performance, while also emphasizing the importance of input samples and feature selection in driving accurate outcomes.
format Article
id doaj-art-0421fdfeb8bc4b07b7af456506585de4
institution OA Journals
issn 2079-3197
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Computation
spelling doaj-art-0421fdfeb8bc4b07b7af456506585de42025-08-20T01:56:19ZengMDPI AGComputation2079-31972025-05-0113511610.3390/computation13050116An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in ColombiaDiego Armando Pérez-Rosero0Diego Alejandro Manrique-Cabezas1Jennifer Carolina Triana-Martinez2Andrés Marino Álvarez-Meza3German Castellanos-Dominguez4Signal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaSignal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaSignal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaSignal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaSignal Processing and Recognition Group, Universidad Nacional de Colombia, Manizales 170003, ColombiaAddressing unemployment is essential for formulating effective public policies. In particular, socioeconomic and monetary variables serve as essential indicators for anticipating labor market trends, given their strong influence on employment dynamics and economic stability. However, effective unemployment rate prediction requires addressing the non-stationary and non-linear characteristics of labor data. Equally important is the preservation of interpretability in both samples and features to ensure that forecasts can meaningfully inform public decision-making. Here, we provide an explainable framework integrating unsupervised and supervised machine learning to enhance unemployment rate prediction and interpretability. Our approach is threefold: (i) we gather a dataset for Colombian unemployment rate prediction including monetary and socioeconomic variables. (ii) Then, we used a Local Biplot technique from the widely recognized Uniform Manifold Approximation and Projection (UMAP) method along with local affine transformations as an unsupervised representation of non-stationary and non-linear data patterns in a simplified and comprehensible manner. (iii) A Gaussian Processes regressor with kernel-based feature relevance analysis is coupled as a supervised counterpart for both unemployment rate prediction and input feature importance analysis. We demonstrated the effectiveness of our proposed approach through a series of experiments conducted on our customized database focused on unemployment indicators in Colombia. Furthermore, we carried out a comparative analysis between traditional statistical techniques and modern machine learning methods. The results revealed that our framework significantly enhances both clustering and predictive performance, while also emphasizing the importance of input samples and feature selection in driving accurate outcomes.https://www.mdpi.com/2079-3197/13/5/116explainabilityunemployment rateregressionlocal biplotUMAPGaussian Processes
spellingShingle Diego Armando Pérez-Rosero
Diego Alejandro Manrique-Cabezas
Jennifer Carolina Triana-Martinez
Andrés Marino Álvarez-Meza
German Castellanos-Dominguez
An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
Computation
explainability
unemployment rate
regression
local biplot
UMAP
Gaussian Processes
title An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
title_full An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
title_fullStr An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
title_full_unstemmed An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
title_short An Explainable Framework Integrating Local Biplots and Gaussian Processes for Unemployment Rate Prediction in Colombia
title_sort explainable framework integrating local biplots and gaussian processes for unemployment rate prediction in colombia
topic explainability
unemployment rate
regression
local biplot
UMAP
Gaussian Processes
url https://www.mdpi.com/2079-3197/13/5/116
work_keys_str_mv AT diegoarmandoperezrosero anexplainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT diegoalejandromanriquecabezas anexplainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT jennifercarolinatrianamartinez anexplainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT andresmarinoalvarezmeza anexplainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT germancastellanosdominguez anexplainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT diegoarmandoperezrosero explainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT diegoalejandromanriquecabezas explainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT jennifercarolinatrianamartinez explainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT andresmarinoalvarezmeza explainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia
AT germancastellanosdominguez explainableframeworkintegratinglocalbiplotsandgaussianprocessesforunemploymentratepredictionincolombia