市场需求组合定性预测的研究

A study of combined qualitative forecastion of the market demand

针对市场需求预测的复杂性和不确定性 ,并考虑定性预测变量如何组合的问题 ,提出使用一种新的组合预测方法 ,即采用Logit回归法训练数据的市场需求组合预测模型 .同时将该方法用于家用电冰箱市场需求趋势预测 ,并采用信息熵的方法 ,检验了组合预测模型的预测效果 .实践证明 ,所提方法具有改变组合权重的优势以及具有较高精度等特点 .

In order to fit in with the development of times, exploring more effective forecasting theory and method is becoming one of the important contents that business and academic circles are concerned about. In the paper, a computationally-convenient means of combined forecasts is introduced, which takes into account how to combine the qualitative forecasting variables, i.e. how to apply Logit regression to the training set data. This method is used in the case of studying the forecasting of the family of the market demand trend of fridge, and at this model of the combined forecasting is tested by the method of information entropy. The practice indicates that it has the advantage of changing the combined weight with more accuracy .