Research on Product Sales Forecast Based on Test Sales Comment Data

Abstract

This study predicts product sales based on product sales during the trial period and text mining of online reviews of products. This study uses the BERT model to judge the sentiment tendency of reviews and identify product attributes, build a sales forecast model based on the extracted review features and the sales and product features during the trial sales period, and evaluate the effect of the forecast model. Among the prediction models constructed in the study, the multiple linear regression model has the worst effect, the prediction effect of random forest and BP neural network is close, and the prediction effect of XGBoost model is the best.