Advanced Design and Development of Information Systems Business Analytics Programming Computers and Information Systems Designs/Analysis of Data Structure and Algorithms Information Security Information Technology in the Digital Era Machine Learning Object Oriented Programming IObject Oriented Programming II Supply Chain Solutions with ERP/SAP I Supply Chain Solutions with ERP/SAP II Analytics for Business Intelligence Business Analytics Programming Business Forecasting Data Analysis & Visualization Data Mining for Finance Decision Analysis Dynamic Pricing and Revenue Management Financial Time Series Interpretation of Data Survey Sampling Quality Management
This article describes methods for machine learning using bootstrap samples and parallel processing to model very large volumes of data in short periods of time. The R programming language includes many packages for machine learning different types of data. Three of these packages include Support Vector Machines (SVM) , Generalized Linear Models (GLM) , and Adaptive Boosting (AdaBoost) . While all three packages can be highly accurate for various types of classification problems, each package performs very differently when modeling (i.e. learning) different volumes of input data. In particular, model fitting for Generalized Linear Models execute in much shorter periods of time than either Support Vector Machines or Adaptive Boosting. In instances where very large datasets must be fitted, learning times for both ADA and SVM appear to grow exponentially rather than in a linear fashion. However, when using a combination of parallel processing and bootstrap sampling all three machine leaning methods can be tuned for optimal performance on both the Linux and Windows platforms.
Review of 100 % Online Business Analytics programs: 12 + offered by Northwestern University, University of California, City University of New York, University of British Columbia, UC Berkeley, Indiana University, Online courses are helpful to those who want to learn about and expand there knowledge in business analytics.
Dr. Guido Möser's insight:
Online Business Analytics Programs in the United States - an Overview.
By Ben Lorica For companies in the early stages of grappling with big data, the analytic lifecycle (model building, deployment, maintenance) can be daunting.
Dr. Guido Möser's insight:
A short article by Ben Lorica / Forbes Magazine about gaining access to the best machine-learning methods.
The part Model Selection: Accuracy and other considerations is interesting.
Besides Revolution, SAS and SPSS I would recomment to evaluate Apache Mahout (http://mahout.apache.org/) - a machine learning library to build scalable machine learning libraries, especially when you are working in Big Data Enironments!