The Future Of Pricing: Leveraging The Impact Of Technology Through Machine Learning In Visual Communication For Dynamic Market Adaptation

Abstract

The study aims at exploring how Machine Learning (ML) can be used to complement dynamic pricing, by introducing visual communication, in order to respond to the dynamic changes in the market. Four ML algorithms, Linear Regression, Random Forest, XGBoost, and K-Nearest Neighbors were utilized and compared by analyzing the dataset of 50,000 records that consisted of prices, the customer engagement performance, and visual design rate. It was concluded that the XGBoost was more predictive and accurate with R 2 of 0.91 compared to Random Forest (0.89), KNN (0.76) and Linear Regression (0.71). Digging further, it was discovered that visual scores of 7 to 10 greatly increased the sales volume by approximately 25 percent and by more than 40 percent in the instance of CTR. Dynamic pricing simulation by using XGBoost had increased the total revenue by 24 percent and the sales volume by 31 percent in comparison to static pricing. Such findings prove the effectiveness of integrating ML-based pricing into visual involvement methods, providing better results. The study allows a company that intends to apply a smart and responsive pricing system to implement a system that is attentive and company-based.