Big data is driving the rapid adoption of data mining and predictive analytics across all industries. While collecting and using data to make better decisions and understand customer behavior has historically been complex and expensive, it is becoming more standardized and affordable as the market matures. The Predictive Model Markup Language standard, or PMML, is one of the key reasons. Please review the article we wrote on Big Data and PMML for the SAP – Big Data Analytics Guide. See our article on page 48.
In this first part of a four-part article series written for the IBM developerWorks website, Dr. Alex Guazzelli gives an overview of predictive analytics and describes how it is able to discover hidden patterns in large data volumes that the human expert may not see. Given that we can apply predictive analytics to a myriad of datasets in different industries and verticals, this article helps you identify a few applications of predictive analytics on your own.
In this second article of a four-part series written for the IBM developerWorks website, Dr. Alex Guazzelli focuses on the predictive modeling techniques themselves, the mathematical algorithms that make up the core of predictive analytics. These include neural networks, support vector machines and decision trees.
In this third article of a four-part series written for the IBM developerWorks website, Dr. Alex Guazzelli discusses the several stages involved in the creation of a predictive solution, including data analysis, feature selection, model building and verification.
In this last article of a four-part series written for the IBM developerWorks website, Dr. Alex Guazzelli focuses on the deployment of predictive analytics, or the process of putting predictive solutions to work using PMML, the Predictive Model Markup Language. Although the article describes how to export PMML files from IBM SPSS Statistics, the same concepts apply to any other tool capable of generating PMML.
In this article written for the IBM developerWorks website, Dr. Alex Guazzelli gives an overview of the Predictive Model Markup Language (PMML) standard. As highlighted in the article, predictive analytics is an integral part of our daily lives. At this very moment, predictive solutions are busy at work, monitoring financial transactions for fraud and abuse, recommending movies and other products, or selecting the next best offer you will get from your favorite store. While predictive analytics can pinpoint an outcome before it actually happens, open standards such as PMML are key ingredients for ensuring that the building and deployment of predictive solutions is application independent and so agile and transparent.
Written by Dr. Alex Guazzelli for the IBM developerWorks website, this article is a follow up to “What is PMML?” (see above). Given that a predictive solution is more than the statistical techniques it harbors, this article dives deeper into PMML, the Predictive Model Markup Language, and explores the transformations and functions that are used for data manipulation. It does that by illustrating the use of data pre-processing and modeling in PMML as it is used to represent a complete predictive solution.
In this article written for the IBM developerWorks website, Dr. Alex Guazzelli gives an overview of the applications of predictive analytics in healthcare and the need for standards, such as PMML, the Predictive Model Markup Language. As digital records and information become the norm in healthcare, they enable the building of predictive analytic solutions, which have the potential to lower cost and improve the overall health of the population. As predictive models become more pervasive, the need for PMML is paramount since it allows for solutions to be transparent and agile and to become dynamic assets that can be put to work right-away.