Using Artificial Neural Network and Linear Regression Approach to Predict Cost in Semiconductor Equipment Industry

• Main Authors: Chih-Tsung Kao, 高誌聰
• Other Authors: Tai-Yue Wang
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/23144818534711323932

碩士 === 國立成功大學 === 工業與資訊管理學系專班 === 94 === In today’s world, because the business environment has become more globalize and the competition has become more dramatic, corporations must make business decisions rapidly and accurately in order to stay competitive. Presently, the salesperson in the semiconductor equipment industry normally relies on assistants' or engineers' data collections before he or she can formulate strategic decisions, but sometimes the data process time can be very time consuming. As a result, it often delays the information delivery. For the meantime, semiconductor equipment is the mainstream of the production assets within the semiconductor industry and is highly related to production line and sales profitability. Due to that reason, the purpose of this thesis is to present a method to help project the cost of manufacturing semiconductor equipment so the salesperson can quickly provide a competitive and profitable quotation to his or her customers. Generally speaking, cost prediction is one of the most important processes within a semiconductor equipment manufacturer, and the calculated cost prediction can affect up to 90% of the equipment list price. A fast and accurate cost prediction not only gives companies the ability to receive higher order volumes but also increases companies' profitability. In most cases, the way to calculate cost of a product is to total the direct materials, direct labors, and manufacturing overheads. However, when a company introduces a new product, because salesperson is not familiar with the material cost, production time, production process, and shipping cost, he or she often relies on engineering or production department to come up with projected equipment quotation. On the flip side, engineering and production department may not fully understand salesperson’s cost prediction and analysis process. For this reason, the predicted cost may not be as accurately and correctly as it should be presented. It is determined that using artificial neural network and regression analysis to come up with a cost prediction model for salesperson is essential. Using the semiconductor equipment cost prediction model, the goal of this thesis is to help improve current salesperson’s cost prediction method and hence increase its accuracy and time efficiency.