Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization
Data-driven approaches in machine learning are increasingly applied in economic analysis, particularly for identifying business cycle (BC) turning points. However, temporal dependence in BCs is often overlooked, leading to what we term single path analysis (SPA). SPA neglects the diverse potential r...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/12/5/678 |
_version_ | 1797264137240182784 |
---|---|
author | David Enck Mario Beruvides Víctor G. Tercero-Gómez Alvaro E. Cordero-Franco |
author_facet | David Enck Mario Beruvides Víctor G. Tercero-Gómez Alvaro E. Cordero-Franco |
author_sort | David Enck |
collection | DOAJ |
description | Data-driven approaches in machine learning are increasingly applied in economic analysis, particularly for identifying business cycle (BC) turning points. However, temporal dependence in BCs is often overlooked, leading to what we term single path analysis (SPA). SPA neglects the diverse potential routes of a temporal data structure. It hinders the evaluation and calibration of algorithms. This study emphasizes the significance of acknowledging temporal dependence in BC analysis and illustrates the problem of SPA using learning vector quantization (LVQ) as a case study. LVQ was previously adapted to use economic indicators to determine the current BC phase, exhibiting flexibility in adapting to evolving patterns. To address temporal complexities, we employed a multivariate Monte Carlo simulation incorporating a specified number of change-points, autocorrelation, and cross-correlations, from a second-order vector autoregressive model. Calibrated with varying levels of observed economic leading indicators, our approach offers a deeper understanding of LVQ’s uncertainties. Our results demonstrate the inadequacy of SPA, unveiling diverse risks and worst-case protection strategies. By encouraging researchers to consider temporal dependence, this study contributes to enhancing the robustness of data-driven approaches in financial and economic analyses, offering a comprehensive framework for addressing SPA concerns. |
first_indexed | 2024-04-25T00:24:07Z |
format | Article |
id | doaj.art-29e1f88a8e53420e92f9ef3bbbee6dcd |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-04-25T00:24:07Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-29e1f88a8e53420e92f9ef3bbbee6dcd2024-03-12T16:49:56ZengMDPI AGMathematics2227-73902024-02-0112567810.3390/math12050678Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector QuantizationDavid Enck0Mario Beruvides1Víctor G. Tercero-Gómez2Alvaro E. Cordero-Franco3Department of Industrial Manufacturing & Systems Engineering, Texas Tech University, Lubbock, TX 79409, USADepartment of Industrial Manufacturing & Systems Engineering, Texas Tech University, Lubbock, TX 79409, USASchool of Engineering and Sciences, Tecnologico de Monterrey, Monterrey 64849, MexicoFacultad de Ciencias Físico Matemáticas, Universidad Autónoma de Nuevo León, San Nicolás de los Garza 66451, MexicoData-driven approaches in machine learning are increasingly applied in economic analysis, particularly for identifying business cycle (BC) turning points. However, temporal dependence in BCs is often overlooked, leading to what we term single path analysis (SPA). SPA neglects the diverse potential routes of a temporal data structure. It hinders the evaluation and calibration of algorithms. This study emphasizes the significance of acknowledging temporal dependence in BC analysis and illustrates the problem of SPA using learning vector quantization (LVQ) as a case study. LVQ was previously adapted to use economic indicators to determine the current BC phase, exhibiting flexibility in adapting to evolving patterns. To address temporal complexities, we employed a multivariate Monte Carlo simulation incorporating a specified number of change-points, autocorrelation, and cross-correlations, from a second-order vector autoregressive model. Calibrated with varying levels of observed economic leading indicators, our approach offers a deeper understanding of LVQ’s uncertainties. Our results demonstrate the inadequacy of SPA, unveiling diverse risks and worst-case protection strategies. By encouraging researchers to consider temporal dependence, this study contributes to enhancing the robustness of data-driven approaches in financial and economic analyses, offering a comprehensive framework for addressing SPA concerns.https://www.mdpi.com/2227-7390/12/5/678data-driven methodstemporal dependenceMonte Carlo simulationrobustnessmultivariate analysiseconomic indicators |
spellingShingle | David Enck Mario Beruvides Víctor G. Tercero-Gómez Alvaro E. Cordero-Franco Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization Mathematics data-driven methods temporal dependence Monte Carlo simulation robustness multivariate analysis economic indicators |
title | Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization |
title_full | Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization |
title_fullStr | Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization |
title_full_unstemmed | Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization |
title_short | Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization |
title_sort | addressing concerns about single path analysis in business cycle turning points the case of learning vector quantization |
topic | data-driven methods temporal dependence Monte Carlo simulation robustness multivariate analysis economic indicators |
url | https://www.mdpi.com/2227-7390/12/5/678 |
work_keys_str_mv | AT davidenck addressingconcernsaboutsinglepathanalysisinbusinesscycleturningpointsthecaseoflearningvectorquantization AT marioberuvides addressingconcernsaboutsinglepathanalysisinbusinesscycleturningpointsthecaseoflearningvectorquantization AT victorgtercerogomez addressingconcernsaboutsinglepathanalysisinbusinesscycleturningpointsthecaseoflearningvectorquantization AT alvaroecorderofranco addressingconcernsaboutsinglepathanalysisinbusinesscycleturningpointsthecaseoflearningvectorquantization |