Predict What Users Will Like

free guidebook: How to Build an Effective Recommendation Engine:
Recommendation engines are built to predict what users might like, especially when there are lots of choices available. They’re critical for certain types of businesses because they can expose users to content they may not have otherwise found or keep users engaged for longer than they otherwise would have been, meaning ultimately increased revenue from more sales or advertising.
In this guidebook you will find:
• An in-depth look at the different types of recommendation engines (as well as the advantages and ideal use cases for each);
• A step-by-step walkthrough to build a recommendation engine from scratch (including code and sample datasets);
• Insights on the specific challenges in exploring, cleaning, and modeling data for a recommendation engine;
• A look into the up-and-coming recommendation engine techniques that cutting-edge enterprises are leveraging.
Get started with our guidebook and give user engagement or sales a boost with a tailored and effective recommendation engine.


Connectionist Models of Cognition

In this video, I give an introduction to the field of computational cognitive modeling (i.e. modeling minds through algorithms) in general, and connectionist modeling (i.e. using artificial neural networks for the modeling) in particular. We deal with the following topics:
• The purpose of computational cognitive modeling
• Where connectionist models fit into the broader picture
• How connectionist models work internally (including an introduction to artificial neural networks)
• A landmark study that models language use with ANNs (“Finding Structure in Time”, Elman, 1990)
• The impact of connectionist modeling on cognitive neuropsychology


Hello, World: Building an AI that understands the world through video

Machines today can identify objects in images, but they are unable to fully decipher the most important aspect: what’s actually happening in front of the camera. At TwentyBN, we have created the world’s first AI technology that shows an awareness of its environment and of the actions occurring within it. Our system observes the world through live video and automatically interprets the unfolding visual scene.


Substitute levels in a factor or character vector

I’ve been using the ggplot2 package a lot recently. When creating a legend or tick marks on the axes, ggplot2 uses the levels of a character or factor vector. Most of the time, I am working with coded variables that use some abbreviation of the “true” meaning (e.g. “f” for female and “m” for male or single characters for some single character for a location: “S” for Stuttgart and “M” for Mannheim). In my plots, I don’t want these codes but the full name of the level. Since I am not aware of any super-fast and easy to use function in base R (let me know in the comments if there is one), I came up with a very simple function and put this in my .Rprofile (that means that it is available whenever I start R). I called it “replace.levels“. The dot before the name means that it is invisible and does not show up in my Global Environment overview in RStudio. You have to call it with .replace.levels(), of course.


Python Built-in Functions and Methods (Python for Data Science Basics #3)

It’s fair to say that using functions is the biggest advantage of Python. At least you will use them a lot during your Data Science projects! This is episode #3 of the “Python for Data Science Basics” series and it’s about the Python functions and methods! In this article I won’t just introduce you to the concept, but will give you a list of the most important functions and methods that you will use all the time in the future.
Advertisements