DynPricing Dataset

DynPricing Dataset v1.0.0 is a processed and chronologically structured dataset designed for dynamic pricing research using Reinforcement Learning. It supports experiments involving LSTM-based demand forecasting and Proximal Policy Optimization (PPO) agents under sequential decision-making settings. The dataset is derived from the Kaggle "Retail Sales Forecasting Data" and was preprocessed to ensure temporal consistency and reproducibility for Markov Decision Process (MDP)-based experimentation.