AI-Driven Pricing Algorithms for Efficient Inventory and Cost Management in Retail

This paper discusses the creation and application of a software that uses AI for pricing and stock management, aimed at improving Koçtaş's pricing strategy and inventory management. The software uses advanced machine learning techniques to examine past sales data, inventory levels, and market conditions, allowing for real-time adjustments to pricing. Integrating the AI system with Koçtaş's current analytical platform improves pricing accuracy, decreases excess stock, and lessens reliance on outside services. This paper discusses the methods used to build the system, covering aspects such as data collection, model development, and system integration. This system greatly simplifies Koçtaş’s pricing processes, minimizes manual errors, and enhances operational efficiency. The software helps improve stock management by decreasing excess inventory, especially for delisted products and those with high SGS values. It also optimizes pricing strategies according to real-time market conditions. Additionally, the system's capability to adjust to market changes helps Koçtaş stay competitive in the retail industry. The paper discusses future improvements, such as refining machine learning models for better accuracy, adding more features to the system, and enhancing scalability and user interface design. This study shows the potential of AI in today's retail pricing and inventory management.