Comparing AI and Traditional Approaches in Dynamic Pricing Models for E-Commerce
Dr. PU Anitha, Kadali Vijayalakshmi, Prasadu Gurram
This research paper provides a comparative analysis of traditional and AI-based dynamic pricing models
in the context of e-commerce. Dynamic pricing plays a pivotal role in optimizing revenue, customer
satisfaction, and profitability for online businesses. Traditional models, such as rule-based, cost-plus,
time-based, and competitor-based pricing, rely on static, predefined rules and limited data, which often
results in suboptimal pricing decisions. On the other hand, AI-based approaches, including machine
learning, reinforcement learning, and neural networks, offer real-time adaptability and personalization
by analyzing vast amounts of data. The experimental results show that AI-based models significantly
outperform traditional approaches, achieving higher revenue, conversion rates, profit margins, and
customer retention rates. This study highlights the critical advantages of integrating AI in dynamic
pricing strategies for e-commerce and its potential to transform the competitive landscape.
