San Diego Training & Conference Center
350 10th Avenue, Suite 950
San Diego, CA 92101
619-235-860 - 619-235-8627 Fax
http://www.sandiegotacc.com
Post-Conference Training Schedule
Introduction to CART® August 26, 2009
Course Outline
This seminar will be held from 9:00 a.m. to approximately 5:00 p.m. with a break for lunch between 12:30 p.m. and 1:30 p.m. Lunch will not be provided. Please arrive at least ten minutes early to sign in and pick up your course materials.
Introduction to CART®: Data Mining with Decision Trees - Discover the power of tree structured data mining during this popular intro tutorial by one of the world's leading experts in CART® (classification and regression tree) technology and real world applications.
TreeNet® & Advanced CART® August 27, 2009
Course Outline Treenet
Course Outline Advanced Cart
This seminar will be held from 8:30 a.m. to approximately 4:30 p.m. with a break for lunch between 12:00 p.m. and 12:30 p.m. Lunch will not be provided. Please arrive at least ten minutes early to sign in and pick up your course materials.
TreeNet®: Stochastic Gradient Boosting - TreeNet stochastic gradient boosting is Jerome Friedman's latest advance in data mining methodology. In TreeNet, classification and regression models are built up gradually through a potentially large collection of small trees, each of which improves on its predecessors through an error-correcting strategy. Individual trees may be as small as one split, but the final models can be extraordinarily accurate and are remarkably resistant to over fitting. Innovations in this methodology include (a) never using all the training data at any one time, (b) a very slow learning rate, and (c) potentially ignoring increasingly large portions of the training data as the model evolves.
Advanced CART® - Sharpen your decision tree expertise during this advanced course, geared towards analysts and modelers with prior knowledge of tree algorithms. Using case studies, seminar topics include (a) hybridizing CART with logistic regression (b) combining multiple trees via bagging, boosting, repeated sampling and varying priors (c) understanding the strategy behind alternative splitting rules and their characteristic strengths, weaknesses and signatures (d) learning how CART implements variable costs of misclassification; separating growing with costs from pruning with costs, and (e) emerging topics in decision trees; highlights of recent developments.
MARS® & RandomForests® August 28, 2009
Course Outline
This seminar will be held from 9:00 a.m. to approximately 5:00 p.m. with a break for lunch between 12:30 p.m. and 1:30 p.m. Lunch will not be provided. Please arrive at least ten minutes early to sign in and pick up your course materials.
MARS® - What is MARS? Why does it work? How can it be used? How can it help you develop more accurate regression models for problems such as predicting credit card holder balances, insurance claim losses, customer catalog orders, and cell phone use? You will learn how to plan and execute a MARS analysis, how to refine models using key control parameters, and how to use MARS to improve existing models.
RandomForests® - RandomForests, is based on learning ensembles of CART trees. By judiciously injecting randomness into the tree building process and then combining hundreds of these trees, RandomForests is able to deliver high performance predictive models and a variety of novel exploratory data analysis results. RandomForests also incorporates new metric free CLUSTER analyses that automatically select the variables used to define each cluster, with potentially different variables defining each cluster.
Post-Conference Training Registration
To be updated with the latest information about the 2009 Salford Systems Data Mining Conference, please click
here.
