Abstract:

The accuracy rate of commodities price forecast based on Web mining is lower because of the network noise. In order to increase this accuracy rate, a novel price forecast method and a comprehensive price forecast model based on the linear backfilling and adaptive sliding windows algorithm were proposed. This comprehensive price forecast model was utilized in the commodities price forecast for cell phone and gold market. Experimental results showed that the mean absolute error of this proposed model could get more than 99 percent accuracy rate. In addition, the antinoise performance of the webpage commodity price data extraction was improved. At the same time,this method could also solve the problem that the existing vendors only had the historical sales price data but did not have the forecasted price based on a plurality of vendors, which could also provide basis for the commodities market forecast and analysis.

Key words: commodity price, data mining, forecasting model, liner backfilling, adaptive sliding windows