@article{Castaneda Sanchez_Polo Escobar_Vega Huincho_2023, title={Artificial neural networks: a measurement of forecast learnings as potential demand}, volume={27}, url={https://uctunexpo.autanabooks.com/index.php/uct/article/view/686}, DOI={10.47460/uct.v27i118.686}, abstractNote={<p>Neural networks today have become an essential technological tool due to their contribution to developing problems related to forecasting learning in production planning to meet potential demand. The research aims to apply artificial neural networks to measure a deep understanding of forecasts. The study is quantitative with a pre-experimental design. A test with pre-test and post-test was used for the Visual Net neural network programming language for each type of programmed learning. The results based on the averages regarding the predictive conceptual understanding and the neural network method were substantial. In contrast, automatic and deep learning contributed to the development of the problem. In terms of a deep understanding of the student’s behaviors is essential. The results of the application of forecasts helped the changes of the neural network in acquiring the ability to learn more complex functions and concluding that artificial neural networks in deep forecasting learning substantially improve learning in concepts, procedures, and behaviors which leads the company to minimize costs and increase profits for various ideas.</p&gt;}, number={118}, journal={Universidad Ciencia y Tecnología}, author={Castaneda Sanchez, Willy Alex and Polo Escobar, Benjamin Roldan and Vega Huincho, Fernando}, year={2023}, month={Feb.}, pages={51-60} }