A prediction study on the car sales based on web search data

Abstract

The automobile industry is a pillar industry in the national economy, so it's of important significance to predict accurately car sales. On the basis of building theoretical frame of web search data and car sales, this paper selects keywords with the technology of auto recommendation, composes the keywords into composite index which can be used in the regression model of this paper, analyzes the relationship between the sales of car in different price ranges and the corresponding composite index, makes the prediction test, finally has the forecast results of car sales in different price ranges whose Prediction MAPE is less than 4 percent.