Net Profit Forecast Based on Improved Support Vector Machine

Abstract

Net profit is an essential economic indicator. For the investors, the net profit is the basic factor to get the return on investment. For the managers, the net profit is the basis for making business management decisions. Since this kind of data usually has data noise and more data dimensions, the traditional forecasting methods often produce errors. For such problems this paper uses several models such as support vector machine, combined with the changes of current net profit factors and the historical data of related enterprise net profit, to predict the enterprise net profit. And we use five indicators, mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), to make a relatively comprehensive and objective evaluation of the forecasting ability of the model.