Optimizing Predictive Accuracy: A Study of K-Medoids and Backpropagation for MPX2 Oil Sales Forecasting

Abstract

This study assesses the use of K-Medoids and Backpropagation methods for predicting MPX2 Oil sales in the automotive workshop industry, crucial for meeting customer demands and refining sales strategies. Using transaction data from 2022 to 2023, the research involved normalizing and processing this data with these algorithms to forecast stock levels, focusing on accuracy measures like Mean Absolute Deviation (MAD) and Mean Squared Error (MSE). K-Medoids aided in identifying customer purchase patterns through clustering, while Backpropagation effectively predicted sales trends, improving accuracy with training. These findings offer valuable insights into MPX2 Oil's sales dynamics, enabling the company to enhance marketing, transaction management, and inventory strategies.