Esta entrada de blog está basada en mi tesis de maestría en ingeniería industrial y economía en la Universidad de los Andes, titulada Optimal Design for Electricity Auctions: A Deep learning approach.

The internal armed conflict in Colombia represents a large portion of the country's history. The dispute for power and territorial control between different armed groups and state institutions has unleashed the violation of human rights.

The study of algorithmic justice emerged in 2011 with Cynthia Dwork [1], who based it on the principle of equal opportunity: all people, regardless of their characteristics, should be able to access the same opportunities and benefits.

Imagine being able to abstract the world in such a way that it is possible to quantitatively evaluate the benefit of taking certain actions over time. The good news is that this is not far-fetched, in fact one of the ways to do it is by using the theory around Reinforcement Learning (RL).

Thanks to advances in computing power; machine and deep learning; and artificial intelligence (AI), applications of technology that once seemed like science fiction are now on the horizon.

Would you be surprised if from one month to the next gasoline went up $2,000 pesos per gallon? The financial data would say no. In simple terms, we can imagine volatility as what we would consider normal movements.

This post is almost entirely equal to my previous post: Modelling Under-reported Spatio-temporal Events. However, following the suggestions of several referees, the emphasis is only on crime events.

It took me a long time to understand the importance of having a purpose to give direction to our Quantil company.

Algorithmic justice in learning models refers to the application of ethical and fairness principles in the development and use of machine learning algorithms.