• The project, implemented using Python, forecasts store sales using historical unit sales data for thousands of items across multiple stores.
• Preprocessing involved handling missing values, encoding categories, and extracting date features, ensuring proper time-series formatting.
• Feature engineering included lag features, rolling stats, store-item patterns, and Ecuador national and local holidays, along with temporal patterns like trends and seasonality.
• ML models: The first used Linear Regression (scikit-learn) for baseline predictions, followed by Deep Learning (LSTM networks with TensorFlow) to improve accuracy by capturing complex temporal patterns.
• A Streamlit dashboard visualized model performance and sales trends with interactive time-series plots and forecast accuracy charts, designed to serve both management and individual store managers.

Real-world business applications of accurate sales forecasting:

• Inventory management: Minimize overstock and stockouts.
• Food waste reduction: Better match supply with demand, especially for perishables.
• Supply chain optimization: Enhance ordering and logistics planning.
• Staffing and resource planning: Align workforce and resources with demand.
• Promotional planning: Assess and optimize marketing campaign impact.

Link to Deep Learning GitHub Repository

Link to Linear Regression GitHub Repository