Demand forecasting plays a critical role in retail by influencing inventory management, supply chain efficiency, and customer satisfaction. Traditional statistical methods, while effective in stable environments, often fail to capture the complex and nonlinear patterns of modern retail data influenced by seasonality, promotions, and changing consumer behavior. With the advancement of Artificial Intelligence (AI), particularly machine learning and deep learning, demand forecasting has shifted toward more adaptive and accurate models. This paper presents a comprehensive study of AI-based demand forecasting models tailored for the retail sector. It examines various techniques, including regression models, decision trees, ensemble methods, neural networks, and deep learning approaches such as Long Short-Term Memory (LSTM) networks. The study highlights the ability of these models to process large, high-dimensional datasets, including both structured and unstructured data such as historical sales, pricing, weather, and consumer sentiment. The proposed framework integrates feature engineering, model training, and performance evaluation using metrics like Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). Results indicate that hybrid models combining statistical and AI approaches improve forecasting accuracy. Overall, AI-based models significantly enhance prediction accuracy, helping retailers optimize inventory, reduce costs, and improve decision-making.
Moussa Camara· International Journal of App...· 0 citations
Smart agriculture is one such technology that has come as a paradigm shift in a quest to deal with increased food security issues, climate changes and scarcity of resources. When the method of machine learning (ML) is integrated in the agricultural system, it allows making intelligent decisions, predictive analytics, and optimising farming processes. The following paper is a comprehensive study of machine learning-based optimization in smart agriculture based on data-driven solutions to the prediction of crop yields, irrigation timing, soil health, pest and disease detection, and resource management. The proposed framework uses supervised, unsupervised, and reinforcement learning frameworks to maximise agricultural production, reduce the environmental costs and operational cost at a minimum level. The modular methodology is proposed which includes the data acquisition using the IoT-enabled sensors, preprocessing of the data, feature engineering, model training, and real-time deployment. The standard evaluation metrics like accuracy, precision, recall, RMSE, and F1-score are used to compare the performance of the two results of the analysis. The findings show that yield prediction using the hybrid algorithm is significantly more accurate, economical in water consumption and increases the early warning of diseases than conventional rule-based and statistical models. This paper identifies the importance of machine learning as a key to the creation of sustainable, resilient, and scalable agricultural systems and informs about the future research directions in the area of intelligent farming ecosystems.
Moussa Camara· International Journal of App...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
