China
Africa
Explore chapters and articles related to this topic
Cutting Edge Data Analytical Tools
Published in Chong Ho Alex Yu, Data Mining and Exploration, 2022
As the name implies, Enterprise Miner is specific for data mining. Like Enterprise Guide, it also adopts a flow-chart-styled interface. Enterprise Miner enables users to step through SAS’s five-step SEMMA approach: sampling, exploration, modification, modeling, and assessment (Azevedo and Santos 2008). Many common data mining features are included in Enterprise Miner, such as decision trees, time series, neural networks, sequence and web path analysis, market basket analysis, and link analysis. More importantly, high performance (HP) procedures are also available in Enterprise Miner. Figure 3.6 shows a typical example of a data mining project implemented in SAS Enterprise Miner. The icon at the bottom right corner symbolizes a high-performance procedure named HP Forest. More details will be explained in Chapter 7.
CRISP-eSNeP: Towards a data-driven knowledge discovery process for electronic social networks
Published in Journal of Decision Systems, 2019
Daniel Adomako Asamoah, Ramesh Sharda
From an industry perspective, the two most popular models in use are the CRISP-DM (Hipp & Lindner, 1999) and SEMMA (Azevedo & Santos, 2008) models. SEMMA is a 5-step model that stands for Sample, Explore, Modify, Model and Assess. It was developed by the SAS Institute. Although it is easy to use, it is closely linked to SAS’s KDDM product, and hence, in some cases could be limited by lack of broader application to other non-SAS KDDM software products. CRISP-DM was developed by a consortium of companies, namely Daimler Chrysler, NCR, OHRA (an insurance company) and SPSS. The 6-step CRISP-DM process is currently the most widely used KDDM process model. It is easy to use, has readily available good documentation and breaks its steps down into smaller iterative steps. A thorough description of key KDDM process models can be found in (Kurgan & Musilek, 2006).