<![CDATA[Central Pacific Development possesses an abundance of sales transaction data, yet currently lacks a system to optimally leverage this data for strategic planning. This research aims to implement an Artificial Neural Network (ANN) using the Backpropagation method to predict product sales, based on historical data from January 2022 to November 2024. The system involves stages such as data normalization, splitting the dataset into training and testing sets, and evaluating model performance using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) metrics. A Multi-Layer Perceptron (MLP) model with a 12-15-1 configuration yielded the best results, achieving a training MSE of 0.000999, a testing MSE of 0.062680, a MAPE of 22.24%, and an accuracy of 77.75%. The developed system can assist the company in designing data-driven production and marketing strategies, while also opening opportunities for further development through the integration of big data technologies or hybrid methods to improve prediction accuracy.]]>
Copyrights © 2025
