Retail Demand Forecasting Using Neural Networks and Macroeconomic Variables

With the growing competition among firms in the globalized corporate environment and considering the complexity of demand forecasting approaches, there has been a large literature on retail demand forecasting utilizing various approaches. However, the current literature largely relies on micro variables as inputs, thereby ignoring the influence of macroeconomic conditions on households’ demand for retail products. In this study, I incorporate external macroeconomic variables such as Consumer Price Index (CPI), Consumer Sentiment Index (ICS), and unemployment rate along with time series data of retail products’ sales to train a Long Short-Term Memory (LSTM) model for predicting future demand. The inclusion of macroeconomic conditions in the predictive model provides greater explanatory power. As anticipated, the developed model, including this external macroeconomic information, outperforms the model developed without this macroeconomic information, thereby demonstrating strong potential for industry application with improved forecasting capability.