Inteligencia de mercado predictiva mediante aprendizaje automático
Mente Biografías y Perspectivas · 2026
DOI: 10.70577/dv06tw18 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mente Biografías y Perspectivas, 2026. Verfasst von Jhon Devis Cuenca Cedeño. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Digital transformation has increased the complexity of business decision-making due to large volumes of data and variability in consumer behavior. The objective of the study was to analyze predictive market intelligence through machine learning as a tool to strengthen strategic decision-making. The methodology was based on a quantitative explanatory approach with a non-experimental design and secondary data analysis from international and national institutions. Multiple linear regression, Spearman correlation, and the Random Forest algorithm were applied using Python and SPSS. The results show that investment in artificial intelligence, commercial automation, and digital personalization explain a high proportion of digital sales growth. Additionally, purchase frequency, browsing time, and price sensitivity were key variables in predicting consumer behavior. The Random Forest model demonstrated high predictive accuracy in classifying customer churn and repurchase behavior. It is concluded that predictive market intelligence through machine learning improves decision-making accuracy, enhances consumer segmentation, and strengthens business competitiveness in dynamic digital environments.
Zitieren
APA
Cedeño, J. D. C. (2026). Inteligencia de mercado predictiva mediante aprendizaje automático. Mente Biografías y Perspectivas. https://doi.org/10.70577/dv06tw18
Vancouver
Cedeño JDC. Inteligencia de mercado predictiva mediante aprendizaje automático. Mente Biografías y Perspectivas. 2026. doi:10.70577/dv06tw18
BibTeX
@article{Cedeo2026,
author = {Cedeño, Jhon Devis Cuenca},
title = {Inteligencia de mercado predictiva mediante aprendizaje automático},
journal = {Mente Biografías y Perspectivas},
year = {2026},
doi = {10.70577/dv06tw18}
}
EUVIMED