Applying Machine Learning in Retail Demand Prediction – A Comparison of Tree-Based Ensembles and LSTM-based Deep Learning
Forecasting plays a pivotal role in decision-making, particularly in retail supply chain management where precise demand and inventory predictions can profoundly influence business operations and profitability. Recent advancements have seen the integration of deep neural networks, such as LSTM, and especially of ensemble learning, such as Extra Trees Regressor (ETR), to enhance prediction accuracy. The code here provides forecasting using tree-based ensemble demand forecasting and deep learning with LSTM networks.
- Extend beyond using only historical demand data by incorporating diverse and also external features, such as weather and COVID-related data.
- Leverage the power of advanced machine learning techniques by employing two state-of-the-art models.