CRISP-DM <ul><li>Cr oss- I ndustry  S tandard  P rocess  </li></ul><ul><li>For  D ata  M ining </li></ul><ul><li>CRISP-DM ...
CRISP-DM Process <ul><li>It is an  iterative ,  adaptive  process: </li></ul><ul><li>Communication of the business problem...
The CRISP-DM Process Model:   An overview of the  life cycle  of a data mining project <ul><li>The model contains  </li></...
Phases of the CRISP-DM Process Model
http://www.crisp-dm.org/index.htm <ul><li>The  sequence  of the phases is not strict.  </li></ul><ul><li>Moving  back and ...
Outline of the 6 phases  <ul><li>Business Understanding </li></ul><ul><ul><li>Focuses on understanding the project  object...
<ul><li>Data Preparation </li></ul><ul><ul><li>Cover all activities to  construct the final dataset  to be fed into the mo...
<ul><li>Evaluation </li></ul><ul><ul><li>Review the steps executed to construct the model, to be certain it properly achie...
瀏覽器 入口網站 客化網站 Web 資料庫 知識庫 / 資料倉儲 資料管理與探勘系統 資料前處理 資料分類 / 整理 資料分析 / 預測 結果展示 更新知識庫 使用者 顧客關係管理 : ... 顧客知 識管理 廠商知 識管理 員工知 識管理 企...
Upcoming SlideShare
Loading in …5
×

6/4 DM補充資料

353 views
266 views

Published on

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
353
On SlideShare
0
From Embeds
0
Number of Embeds
3
Actions
Shares
0
Downloads
9
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

6/4 DM補充資料

  1. 1. CRISP-DM <ul><li>Cr oss- I ndustry S tandard P rocess </li></ul><ul><li>For D ata M ining </li></ul><ul><li>CRISP-DM was conceived in late 1996 by three “veterans” of the young and immature data mining market: DaimlerChrysler (then Daimler-Benz), SPSS (then ISL), and NCR. CRISP-DM succeeds because it is soundly based on the practical , real-world experience of how people do data mining projects. </li></ul>
  2. 2. CRISP-DM Process <ul><li>It is an iterative , adaptive process: </li></ul><ul><li>Communication of the business problem </li></ul><ul><li>Data collection and management </li></ul><ul><li>Data preprocessing </li></ul><ul><li>Model building </li></ul><ul><li>Model evaluation </li></ul><ul><li>Model deployment </li></ul>
  3. 3. The CRISP-DM Process Model: An overview of the life cycle of a data mining project <ul><li>The model contains </li></ul><ul><ul><li>the corresponding phases of a project, </li></ul></ul><ul><ul><li>their respective tasks , and </li></ul></ul><ul><ul><li>relationships between these tasks </li></ul></ul><ul><ul><ul><li>depending on goals , background and interest of the user, and most importantly depending on the data . </li></ul></ul></ul><ul><li>The Version 1.0 Process Guide and User Manual contains step-by-step directions , tasks and objectives for each phase of the Data Mining Process. </li></ul>
  4. 4. Phases of the CRISP-DM Process Model
  5. 5. http://www.crisp-dm.org/index.htm <ul><li>The sequence of the phases is not strict. </li></ul><ul><li>Moving back and forth between different phases is always required. </li></ul><ul><li>It depends on the outcome of each phase which phase, or which particular task of a phase, that has to be performed next. (adaptive) </li></ul><ul><li>The arrows indicate the most important and frequent dependencies between phases. </li></ul><ul><li>The outer circle in the figure symbolizes the cyclic nature of data mining itself. (iterative) </li></ul><ul><li>A data mining process continues after a solution has been deployed. </li></ul><ul><li>The lessons learned during the process can trigger new, often more focused business questions. </li></ul><ul><li>Subsequent data mining processes will benefit from the experiences of previous ones. </li></ul>
  6. 6. Outline of the 6 phases <ul><li>Business Understanding </li></ul><ul><ul><li>Focuses on understanding the project objectives and requirements from a business perspective </li></ul></ul><ul><ul><li>Convert this knowledge into a data mining problem definition , and a preliminary plan designed to achieve the objectives. </li></ul></ul><ul><li>Data Understanding </li></ul><ul><ul><li>Start with an initial data collection </li></ul></ul><ul><ul><li>Proceed with activities in order to get familiar with the data, to identify data quality problems , to discover first insights into the data, or to detect interesting subsets to form hypotheses for hidden information. </li></ul></ul>
  7. 7. <ul><li>Data Preparation </li></ul><ul><ul><li>Cover all activities to construct the final dataset to be fed into the modeling tool(s). </li></ul></ul><ul><ul><li>Preparation tasks are likely to be performed multiple times , and not in any prescribed order. Tasks include table, record, and attribute selection as well as transformation and cleaning of data for modeling tools. </li></ul></ul><ul><li>Modeling </li></ul><ul><ul><li>Various modeling techniques are selected and applied, with optimal parameter values . </li></ul></ul><ul><ul><li>There are several techniques for the same data mining problem type. Some have specific requirements on the form of data. Going back to the last phase is often needed. </li></ul></ul>
  8. 8. <ul><li>Evaluation </li></ul><ul><ul><li>Review the steps executed to construct the model, to be certain it properly achieves the business objectives . </li></ul></ul><ul><ul><li>Check if there is some important business issue not being sufficiently considered. </li></ul></ul><ul><ul><li>At the end of this phase, a decision on the use of the data mining results should be reached. </li></ul></ul><ul><li>Deployment </li></ul><ul><ul><li>Organize and present the result in a way that customers can use it. </li></ul></ul><ul><ul><li>The deployment phase can be as simple as generating a report or as complex as implementing a repeatable data mining process. </li></ul></ul><ul><ul><li>If the customers carry out the deployment steps, they must understand up front the actions needed to use the created models. </li></ul></ul>
  9. 9. 瀏覽器 入口網站 客化網站 Web 資料庫 知識庫 / 資料倉儲 資料管理與探勘系統 資料前處理 資料分類 / 整理 資料分析 / 預測 結果展示 更新知識庫 使用者 顧客關係管理 : ... 顧客知 識管理 廠商知 識管理 員工知 識管理 企業知識管理 顧客知識與 關係管理系統 學習機制

×