查詢結果分析
相關文獻
頁籤選單縮合
題名 | Forecasting and Analysis of Marketing Data Using Neural Networks= |
---|---|
作者 | Yao,Jingtao; Teng,Nicholas; Poh,Hean-lee; Tan,Chew Lim; |
期刊 | Journal of Information Science and Engineering |
出版日期 | 19981200 |
卷期 | 14:4 1998.12[民87.12] |
頁次 | 頁843-862 |
分類號 | 312.2 |
語文 | eng |
關鍵詞 | Artificial neural networks; Marketing decision support systems; Sales forecasting; Marketing mix; Variable reduction; |
英文摘要 | This study aims to incorporate Artificial Neural Networks into a Marketing Decision Support System (MDSS), specifically, by discovering important variablesthat influence sales performance of colour television (CTV) sets in the Singaporemarket using neural networks. Three kinds of variables, expert knowledge, marketinginformation and environmental data, are examined. The information about theeffects of each of these variables has been studied and made available for decisionmaking. However, their comb ined effect is unknown. This study attempts to explorethe combined effect for the benefit of our collaborator, a multinational corporation(MNC) in the consumer electronics industry in Singapore. Putting these threevariables together as input variables results in a neural network model. Neuralnetwork training is conducted using historical data on CTV sales in Singaporecollected over the past one and a half years. Sensitivity analysis is then performed toreduce input variables of neural networks. This is done by analyzing the weights of theinput node connections in the trained neural networks using two different methods.The weaker variables can be excluded, and this results in a simpler model. Further,an R-Square value of almost I is obtained through the inclusion of an Unknownvariable when the network model consisting only of the most influential variables istrained and tested. Knowing the most influential variables, which in this case includeAverage Price, Screen Size, Stereo Systems, Flat-Square screen type and SeasonalFactors, marketing managers can improve sales performance by paying more attention to them. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。