A Classification Model for Collaborative Procurement Strategies
碩士 === 國立交通大學 === 工業工程與管理系 === 88 === In order to offer high quality service, global companies have to integrate resources effectively. The concept of supply chain management therefore emerges. To raise the competitiveness of a supply chain, companies not only integrate their inner resources but als...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2000
|
Online Access: | http://ndltd.ncl.edu.tw/handle/26625927791796517112 |
id |
ndltd-TW-088NCTU0031016 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-088NCTU00310162015-10-13T10:59:52Z http://ndltd.ncl.edu.tw/handle/26625927791796517112 A Classification Model for Collaborative Procurement Strategies 合作採購策略分類模式之構建 Cheng-Yuan Hsieh 謝承遠 碩士 國立交通大學 工業工程與管理系 88 In order to offer high quality service, global companies have to integrate resources effectively. The concept of supply chain management therefore emerges. To raise the competitiveness of a supply chain, companies not only integrate their inner resources but also develop effective collaboration models to cooperate with suppliers. For most global manufacturers, thousands of purchasing items are a normal case. To manually and periodically audit the procurement strategy for each item is a very difficult and costly task. To develop a model using knowledgeable buyer’s experiences to facilitate purchasing and material management activities will be essential. Through a real world case study, the experimental result shows that the neural network can learn the existing procurement rules effectively. For those who don’t have much experience in procurement, this kind of model can provide a guideline to make the decisions. Besides, neural network is capable to process a lot of data quickly. A buyer can periodically audit purchasing items as well as their procurement strategies and make necessary adjustments if price or amount altered. Therefore, the manufacturer can react to market fluctuations faster, and manage procurement items more cost-effective. In this thesis, a logistic regression is also employed to analyze the data. Logistic regression is a multivariate analysis technique. It can help us to identify factors which have significant causal-effect relationship between each procurement model and material attributes. Because neural network is a “black box” and have limited ability to explicitly identify possible causal relationships, logistic regression is complementary to the neural networks. Ching-En C. Lee 李慶恩 2000 學位論文 ; thesis 71 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 工業工程與管理系 === 88 === In order to offer high quality service, global companies have to integrate resources effectively. The concept of supply chain management therefore emerges. To raise the competitiveness of a supply chain, companies not only integrate their inner resources but also develop effective collaboration models to cooperate with suppliers.
For most global manufacturers, thousands of purchasing items are a normal case. To manually and periodically audit the procurement strategy for each item is a very difficult and costly task. To develop a model using knowledgeable buyer’s experiences to facilitate purchasing and material management activities will be essential.
Through a real world case study, the experimental result shows that the neural network can learn the existing procurement rules effectively. For those who don’t have much experience in procurement, this kind of model can provide a guideline to make the decisions. Besides, neural network is capable to process a lot of data quickly. A buyer can periodically audit purchasing items as well as their procurement strategies and make necessary adjustments if price or amount altered. Therefore, the manufacturer can react to market fluctuations faster, and manage procurement items more cost-effective.
In this thesis, a logistic regression is also employed to analyze the data. Logistic regression is a multivariate analysis technique. It can help us to identify factors which have significant causal-effect relationship between each procurement model and material attributes. Because neural network is a “black box” and have limited ability to explicitly identify possible causal relationships, logistic regression is complementary to the neural networks.
|
author2 |
Ching-En C. Lee |
author_facet |
Ching-En C. Lee Cheng-Yuan Hsieh 謝承遠 |
author |
Cheng-Yuan Hsieh 謝承遠 |
spellingShingle |
Cheng-Yuan Hsieh 謝承遠 A Classification Model for Collaborative Procurement Strategies |
author_sort |
Cheng-Yuan Hsieh |
title |
A Classification Model for Collaborative Procurement Strategies |
title_short |
A Classification Model for Collaborative Procurement Strategies |
title_full |
A Classification Model for Collaborative Procurement Strategies |
title_fullStr |
A Classification Model for Collaborative Procurement Strategies |
title_full_unstemmed |
A Classification Model for Collaborative Procurement Strategies |
title_sort |
classification model for collaborative procurement strategies |
publishDate |
2000 |
url |
http://ndltd.ncl.edu.tw/handle/26625927791796517112 |
work_keys_str_mv |
AT chengyuanhsieh aclassificationmodelforcollaborativeprocurementstrategies AT xièchéngyuǎn aclassificationmodelforcollaborativeprocurementstrategies AT chengyuanhsieh hézuòcǎigòucèlüèfēnlèimóshìzhīgòujiàn AT xièchéngyuǎn hézuòcǎigòucèlüèfēnlèimóshìzhīgòujiàn AT chengyuanhsieh classificationmodelforcollaborativeprocurementstrategies AT xièchéngyuǎn classificationmodelforcollaborativeprocurementstrategies |
_version_ |
1716835253356593152 |