https://orbifold.net/default/wp-content/uploads/2016/04/2733f0c6ed474aca7e6b72329bf8cfc7.jpg 514 700 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-04-03 07:41:252018-08-02 08:21:46Scikit parameter tuning
Scikit shines when it comes to hyperparameter optimization. Here the algorithm parameters are referred to as hyperparameters whereas the coefficients found by the machine learning algorithm itself are referred to as parameters. There are mainly…
https://orbifold.net/default/wp-content/uploads/2018/06/MetalFoam.gif 914 1280 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-03-10 14:26:132018-07-01 06:17:26Portfolio optimization applied to marketing
Using modern portfolio theory in digital marketing optimization.
https://orbifold.net/default/wp-content/uploads/2016/02/OrganizedBlobs.png 483 521 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-02-03 08:32:272018-08-02 08:31:17Unbalanced data (SMOTE)
Intro Imbalanced data typically refers to a problem with classification problems where the classes are not represented equally.For example, you may have a 2-class (binary) classification problem with 100 instances (rows). A total of 80 instances…
https://orbifold.net/default/wp-content/uploads/2016/01/AbstractFlow.png 533 800 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-01-06 19:37:252018-08-02 08:36:05Technical recipe to embrace AI
Simple recipe to get started in AI.
https://orbifold.net/default/wp-content/uploads/2016/01/MarkovChain0.png 1137 1168 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-01-06 17:41:042018-05-20 06:53:30Tutorial: Markov chain in R/C++
The code of this article can be found on Github. This tutorial shows you that creating C++ packages for R is really easy. I have taken a Markov chain as an example but you can invent plenty of other things in the same way. In fact, there…
https://orbifold.net/default/wp-content/uploads/2016/01/CustomerJourney0-1.png 982 2035 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-01-04 06:45:432018-08-02 08:37:27A year of R-esearch
https://orbifold.net/default/wp-content/uploads/2016/01/text-patterns.jpg 1018 1024 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2016-01-01 00:00:002018-05-20 07:13:23Transforming text into data
Ways to transform text into data.
https://orbifold.net/default/wp-content/uploads/2015/11/Blobsvoron.jpg 1024 1024 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2015-11-11 07:47:312018-08-02 15:10:45Filtering out noise with chi2
Using chi2 to find signals in noisy data.
https://orbifold.net/default/wp-content/uploads/2015/11/BinarySquares.jpg 700 700 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2015-11-02 09:47:352018-08-02 15:14:38R integration in SQL Server 2016
Microsoft bought Revolution Analytics for its enterprise-level R spectrum and it was swiftly integrated into the latest SQL Server.
https://orbifold.net/default/wp-content/uploads/2015/10/NetBlobs.jpg 632 948 Orbifold /default/wp-content/uploads/2016/11/OrbifoldNextLogo.png Orbifold2015-10-20 13:44:522018-08-02 15:16:26Classification, dimensional reduction and chi2.
When talking about dimensional reduction in the context of machine learning you have many options; linear discriminant analysis (LDA), principal component analysis (PCA) and many other. Here I want to highlight a technique that I explored as part of a very large research project and which entails the usage of chi2.