Intelligent sales volume forecasting using Google search engine data

Business forecasting is a critical organizational capability for both strategic and tactical business planning. Improving the quality of forecasts is thus an important organization goal. In this paper, the intelligent sales volume forecasting models are constructed using grey analysis, deep learning (DNN), and least-square support vector regression (LSSVR) optimized through particle swarm optimization or genetic algorithm. First, features (predictors) from economic variables are extracted through grey analysis. The selected features together with Google Index, an exogenous variable used widely by researchers, are then used as the inputs to the DNN and LSSVR to build the models. The experimental results indicate that the grey DNN model, an emerging and pioneering artificial intelligence technology, can accurately predict sales volumes based on non-parametric statistical tests. DNN also outperformed the competing models when using Google Index.