Unlocking Your Sales Insights: Advanced XGBoost Forecasting Models for Amazon Products

TL;DR

This paper presents an advanced XGBoost-based forecasting approach for Amazon product sales, demonstrating improved accuracy over traditional models by using sales range data instead of raw volume.

Contribution

The study introduces a novel application of XGBoost with sales range data for better sales prediction accuracy on e-commerce platforms.

Findings

XGBoost outperforms traditional models in sales forecasting.

Replacing sales volume with sales range improves prediction accuracy.

The approach is effective for consumer electronics on Amazon.

Abstract

One of the important factors of profitability is the volume of transactions. An accurate prediction of the future transaction volume becomes a pivotal factor in shaping corporate operations and decision-making processes. E-commerce has presented manufacturers with convenient sales channels to, with which the sales can increase dramatically. In this study, we introduce a solution that leverages the XGBoost model to tackle the challenge of predict-ing sales for consumer electronics products on the Amazon platform. Initial-ly, our attempts to solely predict sales volume yielded unsatisfactory results. However, by replacing the sales volume data with sales range values, we achieved satisfactory accuracy with our model. Furthermore, our results in-dicate that XGBoost exhibits superior predictive performance compared to traditional models.