Preventing Overfitting and Underfitting in Machine Learning Model Development: A Practical Analysis

Iván Calderón Carrillo J. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2026) · DOI: 10.18687/laccei2026.1.1.520

Resumen

The main objective of this document is to develop a guide, supported by a comparative case study, to help future researchers identify fit problems in predictive models used in machine learning. To this end, theoretical aspects were addressed, and, most importantly, a practical case study based on synthetic data was presented. Three predictive models were constructed using synthetic data: an underfitted model, an overfitted model, and an ideal model. This analysis allowed for the identification of the characteristics of each type of fit. Finally, a simple, practical guide was proposed outlining the steps to follow to obtain a model with an adequate fit, that is, one with good generalization capabilities..

Instituciones: Universidad Privada del Norte