This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
The hype around Artificial Intelligence (AI) reached a fevered pitch as the world entered 2019. But what does AI really mean? And how is it related to similarly mystifying terms like ML (machine learning) or ‘deep-learning’?
Have you struggled to deploy your predictive models in a timely manner before they become obsolete? This article will show you how Alteryx Promote solves this challenge by deploying your model into a RESTful API that can be called from a wide variety of enterprise applications.
There are two types of model errors when making an estimate; bias and variance. Understanding both of these types of errors, as well as how they relate to one another is fundamentally important to understanding model overfitting, underfitting, and complexity.
Understanding the topic of a piece of writing is typically an easy task for people. However, there are times where we need to train our computers to find topics in a collection of documents. There might be too many documents for you, a single human, to read through, or you may be interested in discovering underlying themes in a large set of texts. Enter LDA, a popular model for Topic Modeling.
After training a Phrases model with Community texts, I wanted to be able to incorporate the model into Alteryx workflows that I was using to process text, and hopefully even be able to share the model with other Alteryx users. After thinking through this, I realized it was a perfect application for the Python SDK.
Word embeddings are vector representations of words, where more similar words will have similar locations in vector space. First developed by a team of researchers at Google led by Thomas Mikolov, and discussed in the paper Efficient Estimation of Word Representations in Vector Space, word2vec is a popular group of models that produce word embeddings by training shallow neural networks. In this blog post, we apply a word2vec model to the Alteryx Community texts to develop Alteryx-specific word embeddings.
Reproducibility, the open sharing of data, and expanding on the research of others are all at the heart of the scientific process, and we live in an exciting time where it is more possible than ever. This year's Inspire Europe Closing Keynote speaker Dr. Ben Goldacre has recently published a paper examining compliance with the European Commission's guideline that all Clinical Trials registered in the EU Clinical Trials Register must report results to the European Medicines Agency within 12 months of the trial's completion. The bulk of the paper's analysis was performed in the statistical software Stata. With tools like Alteryx or Python, we have easy and open-source ways to process data and derive new knowledge. In this blog, we reproduce some of Goldacre et al.'s analysis in Alteryx and Python and provide both formats for you to further explore the data on your own.
Neural Networks are an approach to artificial intelligence that was first proposed in 1944. Modeled loosely on the human brain, Neural Networks consist of a multitude of simple processing nodes (called neurons) that are highly interconnected and send data through these network connections to estimate a target variable. In this article, I will discuss the structure and training of simple neural networks (specifically Multilayer Perceptrons, aka "vanilla neural networks"), as well as demonstrate an example neural network created by the Alteryx Neural Network Tool.
Who doesn’t love a good cheat sheet? Nobody, that’s who. Cheat sheets are awesome. They are a great reference for functions you need handy, but don’t have memorized by heart (yet). They can also be a fantastic way for learning and reinforcing components of a programming language. Some people like to keep them saved as a bookmark on their web browser. With all of that in mind, we are proud to present to you an Alteryx – R Cheat Sheet, which features Alteryx specific functions for use in the R Tool. With this cheat sheet, you should be better equipped to take on any R Tool challenges you encounter.
Building my first linear regression model turned me into an instant celebrity. My roommate, who has acted as a sounding board for my predictive-analytics-learning progress, now believes I can use Linear Regression to predict the winner of the next horse race. While it would be fun to try, a more applicable use case is predicting how much a customer will spend (which, in the case of horse racing could translate to how much someone might spend on a bet). For my use case, I want to predict how much a Lyft driver can expect to receive on their next fare.
Ever wondered how to build a new analytic tool from scratch using the Alteryx Python SDK, but didn’t know where to start? This blog post takes you through the absolute basics to get you up and running - You’ll be creating brand new tools, connectors and advanced analytics in no time with this step-by-step beginners guide!
Voronoi Tesselation and Delaunay Trianglulation both perform spatial calculations on a set of irregular points. Voronoi Cells (sometimes referred to as Thiessen Polygons in the GIS world) make up a Voronoi Tesselation, which is the partitioning of a plane into polygons based on a set of points, so that for each point there is a corresponding polygon where the area in the polygon is closer to the corresponding point than any other point. Delaunay Triangulation is when a set of irregular points are divided into triangles, so that no point in the set is inside the circumcircle of any triangle created from the points.
Both of these processes have a bunch of really neat spatial analysis applications. In this article, we will talk about their implementation in Alteryx.