Uplift modeling, also known as incremental modeling, true lift modeling, or net-lift modeling is a predictive modeling technique that directly models the incremental impact of a treatment (such as a direct marketing action) on an individual’s behavior. Uplift modeling has applications in customer relationship management for up-sell, cross-sell and retention modeling. It has also been applied to personalized medicine. Unlike the related Differential Prediction concept in psychology, Uplift modeling assumes an active agent.
Implementing a Neural Network from Scratch – An Introduction
In this post we will implement a simple 3-layer neural network from scratch. We won’t derive all the math that’s required, but I will try to give an intuitive explanation of what we are doing. I will also point to resources for you read up on the details.
August 2015: Scripts of the Week
Our August Scripts of the Week all have one thing in common: their goal of teaching the community something new. Some of those learnings are data science specific (e.g. How do EEG domain experts approach datasets?) and others are about universal issues like gender & wage. We can’t promise you the world, but we can promise that reading this blog will almost certainly teach you something new.
Spark SQL for Real-Time Analytics
Apache Spark is the hottest topic in Big Data. This tutorial discusses why Spark SQL is becoming the preferred method for Real Time Analytics and for next frontier, IoT (Internet of Things).
Revolution R Open 3.2.2 now available
Revolution R Open, the enhanced open source R distribution from Revolution Analytics and Microsoft, is now available for download. This update brings multi-threaded performance to the latest update to the R engine from the R Core Group, which includes several improvements and bug fixes. Significant amongst these is default support for HTTPS connections, making it easy to follow the best practices for R security recommended by the R Consortium.
Linear models with weighted observations
In data analysis it happens sometimes that it is neccesary to use weights. …
Have you ever think about accepting payments in your shiny app? Probably not, but now you can start 😉 Shiny apps are usually single task, not very heavy websites. It may be not so easy to turn them into online shop/service provider. Anyway you can find this post interesting as it presents a paperwork-less implementation to accept payments.
Bootstrap Evaluation of Clusters
An important question when evaluating clusters is whether a given cluster is “real”-does the cluster represent actual structure in the data, or is it an artifact of the clustering algorithm? This is especially important with clustering algorithms like k-means, where the user has to specify the number of clusters a priori. It’s been our experience that clustering algorithms will often produce several clusters that represent actual structure or relationships in the data, and then one or two clusters that are buckets that represent “other” or “miscellaneous.” Clusters of “other” tend to be made up of data points that have no real relationship to each other; they just don’t fit anywhere else.
The tutorials on this site were created for the R courses taught by Paul Hiemstra. They are available freely for personal use, which includes individual people working at companies using this material to educate themselves. See the License section below for more details. The tutorials are organized in a number of categories. The order to do them is roughly from top to bottom, as some of the tutorials assume you have knowledge covered in the previous tutorials.
Data science is big landscape and self-learning is the necessary skill if anyone wants to become a good data scientist. MOOCs had been Major source of treasure for the data scientist. Though there are many sites offering MOOCs, but Coursera, Edx and Udacity have been leaders. Whether, your language is R, python, Java or C/C++ we have captured all of them. If, you are a beginner and understanding what data science is exactly or you are an expert looking for your next frontiers. You can search through this exhaustive list as per needed. In this post we have kept only single courses, will write a separate post for the specializations or degrees related to data science. There are some upcoming promising courses in this list too.