整合獨立成份分析與集群技術建構電子產品銷售預測模式

銷售預測在各產業都是相當重要的一部分，因為其會影響商品備貨的多寡及價格訂定，而由於資訊產業環境變化較其他產業都來得迅速，在加上近年來科技與信息快速發展，讓電子產品的銷售變化更無法掌握，因此，如何建構有效的電子商品銷售預測模式成為一個具挑戰性的議題。本研究應用獨立成份分析(independent component analysis, ICA)、集群演算法(clustering)與支援向量迴歸(support vector regression, SVR)建構混合式預測模型於電子產品銷售預測。所提之混合式預測模型先藉由ICA將原始資料投影至特徵空間觀察潛在資訊，之後利用集群技術將具相似特徵之銷售期間分至同一群組，在找出與待預測週期最相似的集群後，用此一集群的資料建構SVR預測模式以進行銷售預測。由於所提之混合預測模式能夠利用特徵萃取方法凸顯出潛在有用的資訊，並且針對待預測資料利用群聚技術找出最適當的訓練資料以建構預測模式，因此能夠提高銷售預測之準確度。本研究以台灣某資訊產品代理商之銷售量資料，以及某電腦產品經銷商之銷售總額資料做為實證研究對象。結果顯示本研究提出之混合模型有明顯優於單一SVR模型與單純結合集群技術與SVR模型的預測結果。

關鍵字

獨立成份分析；支援向量迴歸；集群技術；銷售預測

並列摘要

Sales prediction is an important issue for most enterprise in every industry. It will influence how many products need to be replenished and what price should be made. However, changes in the electronic industry are rapider than others, so forecasts are even more difficult, how to construct a good prediction model for electronic products is a very important thing. In this research, a sales forecasting model which combines independent component analysis(ICA)、clustering technique and support vector regression (SVR) forecasting method is proposed. First, use ICA to transform the input space composed of financial data into the feature space consisting of independent components (ICs) representing underlying information in the original input data, then use clustering to divides the dataset into clusters that assemble the periods with similar characteristics in same group, and choose the most representative group as the training sample to build the SVR model. A weekly sales data from a present leading computer company in Taiwan and a monthly sales data from a electronic company is used as illustrative example. The experimental results showed that the proposed combined clustering method can provide a promising forecasting result.

並列關鍵字

Independent Component analysis ； Support Vector Regression ； Sales Forecasting ； Clustering

參考文獻

[4]. 黃郁仁，整合案例式推理與類神經網路於新產品銷售預測-以圖書產品為例，碩士論文，私立元智大學工業工程與管理學系，桃園，2004。

[5]. 楊榮力，以非線性獨立成份分析、支援向量迴歸及類神經網路建構財務時間序列預測模型，碩士論文，國立台北科技大學商業自動化與管理所，台北，2009。

[10]. A. Honkela, J. Seppa, E. Alhoniemi, “Agglomerative independent variable group analysis,” Neurocomputing, vol. 71 , 2008, pp. 1311-1320.

[11]. A. Hyvärinen and E. Oja, “Independent component analysis: algorithms and applications,” Neural Networks, vol. 13, 2000, pp. 411-430.

[12]. A. Hyvärinen, “Fast and robust fixed-point algorithms for independent componen analysis,” IEEE Transactions on Neural Network, vol. 10, no. 3, 1999, pp. 626-634.

國際替代計量

整合獨立成份分析與集群技術建構電子產品銷售預測模式

未授權

主題瀏覽