Abstract
Online businesses continue to experience rapid development along with digital transformation that drives efficiency and competitiveness. However, one of the main challenges faced is the uncertainty in predicting sales, which can cause an imbalance between demand and stock. The inaccuracy of this prediction often results in overstock or understock, thus increasing operational costs and decreasing customer satisfaction levels. This study aims to analyze the effect of implementing Machine Learning (ML) algorithms on the accuracy of sales predictions and the efficiency of stock management in online businesses. Historical sales data collected from e-commerce platforms were processed using Random Forest and Long Short-Term Memory (LSTM) algorithms. The results showed that the ML algorithm was able to increase the accuracy of sales predictions by up to 20% compared to traditional methods. In addition, the implementation of ML-based predictions allows for more efficient stock management with a decrease in the level of overstock by 15% and a reduction in the risk of understock by up to 25%. These findings not only strengthen the literature related to the role of intelligent technology in digital business management but also offer practical guidance for online business actors to improve their operations through Machine Learning technology. Thus, this study makes an important contribution to digital transformation strategies in a competitive online business ecosystem.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call