Synthetic Retail Demand and Sentiment Datasets for Customer Intelligence and Inventory Optimisation Research

Synthetically generated retail demand dataset (sales.csv, 186,189 product ASINs × 60 months) and curated Amazon Fashion sentiment test files, constructed for proof-of-concept evaluation of a DQN inventory optimisation and DistilBERT sentiment analysis framework. The demand dataset has no external source and was manually constructed for this research. The sentiment data is derived from the publicly available Amazon Reviews 2023 dataset (https://amazon-reviews-2023.github.io).