Predictive Polynomials from Fitting Strategies Based on the Probabilistic Bayes Theorem

Nieto-Chaupis H. · Proceedings - 2025 8th Asia Conference on Cognitive Engineering and Intelligent Interaction, CEII 2025 (2025) · DOI: 10.1109/ceii67787.2025.00060

Resumen

We presented a fitting approach based in the Bayes rule and polynomials that would encompass into a scheme of prediction. More than to carry out fitting procedures or regression, for example, the present proposal employs the polynomials in order to tune in the expected behavior. Thus for example, when data has instabilities and stochastic fluctuations, the modeling by using Bayes in conjunction to polynomials, would represent an alternative path to make prediction for reduced slots of time, for example. Thus, the product of polynomals would play a noteworthy role as to determine the best approximations for fitting data. The case for predicting the number of infections after 25 weeks in a global pandemic, illustrates the features of this study, by which it is deeply desirable to estimate trends to assess the impact of pandemic.

Instituciones: Universidad Autónoma del Perú