Detalhes do Documento

Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics

This project studies the possibility of retail sales forecasting through an artificial intelligence approach, using an in-depth analysis of a prominent sportswear company as a case study. To build a robust foundation, a thorough review of past research in this field, the approaches adopted, and the results reached was made. We extracted real-case observations and addressed their issues to ensure they were satisfactory for a machine-learning model application. Finally, granular forecasts were built starting on a product level and then aggregating to derive an overall forecast for the whole retailer. This project aims to highlight the importance of predictive analytics in decision-making and emphasize the ongoing need for improvement in dynamic retail through collaborative efforts between data science and business intuition. It serves as a testament to the potential of enhancing sales forecasting methodologies, paving the way for more accurate and adaptive predictions in the future.