How Things Work – Page 2 – Learning Machines

Recidivism: Identifying the Most Important Predictors for Re-offending with OneR

In 2018 the renowned scientific journal science broke a story that researchers had re-engineered the commercial criminal risk assessment software COMPAS with a simple logistic regression (Science: The accuracy, fairness, and limits of predicting recidivism).

According to this article, COMPAS uses 137 features, the authors just used two. In this post, I will up the ante by showing you how to achieve similar results using just one simple rule based on only one feature which is found automatically in no-time by the OneR package, so read on!
Continue reading “Recidivism: Identifying the Most Important Predictors for Re-offending with OneR”

Pseudo-Randomness: Creating Fake Noise

In data science, we try to find, sometimes well-hidden, patterns (= signal) in often seemingly random data (= noise). Pseudo-Random Number Generators (PRNG) try to do the opposite: hiding a deterministic data generating process (= signal) by making it look like randomness (= noise). If you want to understand some basics behind the scenes of this fascinating topic, read on!
Continue reading “Pseudo-Randomness: Creating Fake Noise”

ELIZA Chatbot in R: Build Yourself a Shrink

More and more companies use chatbots for engaging with their customers. Often the underlying technology is not too sophisticated, yet many people are stunned at how human-like those bots can appear. The earliest example of this was an early natural language processing (NLP) computer program called Eliza created 1966 at the MIT Artificial Intelligence Laboratory by Professor Joseph Weizenbaum.

Eliza was supposed to simulate a psychotherapist and was mainly created as a method to show the superficiality of communication between man and machine. Weizenbaum was surprised by the number of individuals who attributed human-like feelings to the computer program, including his own secretary!

If you want to build a simple Eliza-like chatbot yourself with R read on!
Continue reading “ELIZA Chatbot in R: Build Yourself a Shrink”

How to Catch a Thief: Unmasking Madoff’s Ponzi Scheme with Benford’s Law

One of my starting points into quantitative finance was Bernie Madoff’s fund. Back then because Bernie was in desperate need of money to keep his Ponzi scheme running there existed several so-called feeder funds.

One of them happened to approach me to offer me a once-in-a-lifetime investment opportunity. Or so it seemed. Now, there is this old saying that when something seems too good to be true it probably is. If you want to learn what Benford’s law is and how to apply it to uncover fraud, read on!
Continue reading “How to Catch a Thief: Unmasking Madoff’s Ponzi Scheme with Benford’s Law”

“You Are Here”: Understanding How GPS Works

Last week, I showed you a method of how to find the fastest path from A to B: Finding the Shortest Path with Dijkstra’s Algorithm. To make use of that, we need a method to determine our position at any point in time.

For that matter, many devices use the so-called Global Positioning System (GPS). If you want to understand how it works and do some simple calculations in R, read on!
Continue reading ““You Are Here”: Understanding How GPS Works”

Finding the Shortest Path with Dijkstra’s Algorithm

I have to make a confession: when it comes to my sense of orientation I am a total failure… sometimes it feels like GPS and Google maps were actually invented for me!

Well, nowadays anybody uses those practical little helpers. But how do they actually manage to find the shortest path from A to B?

If you want to understand the father of all routing algorithms, Dijkstra’s algorithm, and want to know how to program it in R read on!
Continue reading “Finding the Shortest Path with Dijkstra’s Algorithm”

Local Differential Privacy: Getting Honest Answers on Embarrassing Questions

Do you cheat on your partner? Do you take drugs? Are you gay? Are you an atheist? Did you have an abortion? Will you vote for the right-wing candidate? Not all people feel comfortable answering those kinds of questions in every situation honestly.

So, is there a method to find the respective proportion of people without putting them on the spot? Actually, there is! If you want to learn about randomized response (and how to create flowcharts in R along the way) read on!
Continue reading “Local Differential Privacy: Getting Honest Answers on Embarrassing Questions”

Kalman Filter as a Form of Bayesian Updating

The Kalman filter is a very powerful algorithm to optimally include uncertain information from a dynamically changing system to come up with the best educated guess about the current state of the system. Applications include (car) navigation and stock forecasting. If you want to understand how a Kalman filter works and build a toy example in R, read on!
Continue reading “Kalman Filter as a Form of Bayesian Updating”

Learning Data Science: A/B Testing in Under One Minute

Google does it! Facebook does it! Amazon does it for sure!

Especially in the areas of web design and online advertising, everybody is talking about A/B testing. If you quickly want to understand what it is and how you can do it with R, read on!
Continue reading “Learning Data Science: A/B Testing in Under One Minute”

Will AI become conscious any time soon?

We all know the classical Sci-Fi trope of intelligent machines becoming conscious and all the potential ramifications that could follow from there (free will, fighting their human creators, ethical dilemmas, and so forth). Now, is this a realistic scenario? As a researcher in the area of AI (see e.g. So, what is AI really?), with a penchant for philosophy, I share my thoughts here with you, so read on!
Continue reading “Will AI become conscious any time soon?”