Archive

Posts Tagged ‘data mining’

Basic Business Intelligence Reporting

January 23rd, 2012 1 comment

Take a CSV file and perform basic BI and reporting using a free tool.

Duration : 0:7:6

Read more…

Data Mining, Introduction of Beverage Manufacturing Data – Session 23

January 15th, 2012 No comments

This session introduces a data set that will be used to explore the use of data mining tool for the regression problem. The data, beverage manufacturing, has a continuous target variable. The goal of the data mining project is to determine what variables are good predictors of this continuous variable and to train data mining models to predict it. This session reviews the data mining project goals, reviews the data using basic statistics and graphs, and selects appropriate variables. http://statsoft.com/products/data-mining-solutions/

Duration : 0:9:58

Read more…

Chris Hote of Digimind – The Intelligence Collaborative Washington, DC 10/22/09

January 6th, 2012 No comments

Chris Hote of Digimind explains his company’s web tracking and visualization software.

Duration : 0:1:38

Read more…

Manage the Data Deluge with Data Mining and Predictive Analytics

January 6th, 2012 No comments

Learn how data mining can be applied to identify trends, patterns and relationships while predictive analytics can be used to predict future outcomes.

To learn more about data mining and predictive analytics, visit http://www.sas.com/technologies/analytics/datamining/index.html .

Duration : 0:2:28

Read more…

Data Mining, C&RT for Regression – Session 24

December 29th, 2011 No comments

Previously in the series, C&RT and other tree algorithms were discussed for the classification problem. This session uses the regression data, beverage manufacturing, to explore C&RT as well as the other tree algorithms. The options and parameters are reviewed as well as important output. An example analysis is performed in STATISTICA using C&RT. Then the Data Mining Workspace is used to very briefly show the remaining tree tools offered, CHAID, Boosted Trees and Random Forests. http://statsoft.com/products/data-mining-solutions/

Duration : 0:9:3

Read more…

Artificial Intelligence Lecture No. 17

December 21st, 2011 No comments

Video of the Lecture No. 17 in Artificial Intelligence at Ravensburg-Weingarten University from December 5th 2011. The Topics are:

Clustering:
– k-Means and the EM Algorithm
– Hierarchical Clustering
– Distance between Clusters
– Farthest Neighbour Algorithm

Data Mining in Practice
– The Data Mining Tool KNIME

Duration : 1:32:28

Read more…

Machine Learning (Introduction + Data Mining VS ML)

December 21st, 2011 No comments

lemiffelearninghttp://gdata.youtube.com/feeds/api/users/lemiffelearningEducationmachine learning, introduction, data mining, VS machine learningMachine Learning (Introduction + Data Mining VS ML)

Duration : 0:8:31

Read more…

SAS Customer Intelligence Drives Profitable Growth Opportunities

December 13th, 2011 No comments

With SAS Customer Intelligence, you can sharpen your focus on those customers, segments, and market offers that generate the most lucrative growth.

Learn more about SAS Customer Intelligence at: http://www.sas.com/software/customer-intelligence/profitable-growth-opportunities.html .

Duration : 0:2:38

Read more…

Data Mining, Comparing Model Performance – Session 21

December 5th, 2011 1 comment

With the Credit Scoring data, Data Mining models have been built including Classification and Regression Trees, CHAID trees, Random Forest and Boosted Trees. This session will look at STATISTICA tools to deploy these models and compare the results. Lift and Gains charts are used to visually gauge model performance. The Rapid Deployment tool of STATISTICA can be used to deploy many other statistical and data mining models as well. http://statsoft.com/products/data-mining-solutions/

Duration : 0:7:44

Read more…

Data Mining, Random Forest Tools – Session 20

November 28th, 2011 No comments

Session 20 of the Data mining series covers the Random Forest tool. Random Forest build a series of classification trees, each of which is able to classify the target variable. The Random Forest classification is based on the collection of classifications from the individual trees. Performance gains come from using this network of classifiers. This session discusses Random Forest in general, then uses the credit scoring data to give an example of the analysis and results. http://statsoft.com/products/data-mining-solutions/

Duration : 0:6:43

Read more…