Quick commerce (Q-commerce) has transformed retail by enabling ultra-fast deliveries, requiring optimised product assortment and inventory management. While traditional e-commerce offers a broad product range and competitive pricing, its delivery limitations led to Q-commerce’s emergence, ensuring fulfilment within 30 min to a few hours. This study applies prescriptive analytics, machine learning and optimisation algorithms to enhance decision-making in Q-commerce. Advanced forecasting models, such as LSTM networks, improved demand forecasting with a Mean Absolute Error (MAE) of 0.25 and Root Mean Square Error (RMSE) of 0.35, reducing inventory costs by 10%. Linear programming optimised product mix, increasing sales by 15%. LSTM demonstrated high accuracy in predicting demand patterns, ensuring the availability of high-demand products while minimising overstock. Market Basket Analysis (MBA) revealed significant product associations, streamlining fulfilment centre operations and enhancing cross-selling strategies. Market Basket Analysis (MBA) using the Apriori algorithm identified key product associations, reducing picking times by 20% and boosting order value by 12%, contributing to a 15% rise in overall sales. Personalised recommendation systems using collaborative and content-based filtering increased conversion rates by 20% and customer retention by 15%. Despite these advancements, challenges in computational feasibility and synthetic data applicability persist. Future research should focus on real-time analytics and adaptive inventory strategies to enhance scalability and efficiency.