Introduction to shapley values II: a deep dive into its business applications Welcome to my second post about one of the coolest solutions to cooperative problems I have seen in a while. Truth be told, I don’t check as many of them as you would expect for a guy with a blog, but, even so, … Read more
Introduction to Shapley values, what are they, and how are they calculated With the rise of explainable machine learning as an integral part of the ever-growing ml-Ops philosophy, Shapley values have been put in the spotlight in the data-science community as an integral part to make the most of applied ml solutions. This post will … Read more
Hypothesis testing as a key mathematical tool for data-driven strategy Hi! Welcome to this article! This is my first time writing for Medium in what, I hope, will become a hobby in which I’ll indulge more often. I’m not a professional writer but I believe I’m very passionate about the topic that interests me. Learning … Read more
El bosque aleatorio es un tipo de algoritmo que consiste en un conjunto de múltiples árboles de decisión. Si aún no lo has hecho, te recomiendo que le eches un vistazo a este post sobre árboles de decisión, ya que son esenciales para entender bien cómo funcionan los bosques aleatorios. Básicamente lo que vamos a … Read more
Random forest is a type of algorithm that consists of an ensemble of multiple decision trees. If you have not done it yet, I recommend you to check this post on decision trees , as they are essential to fully understanding how random forest works. Basically what we will do, is define a specific type … Read more
Today I’m going to perform a real data analysis case with Power BI. The idea of these posts is to serve as an accelerator tutorial showing in a didactical, fast and effective manner the most important aspects and knowledge needed to work effectively in power BI. We are going to work with a real dataset, … Read more
Qué es la probabilidad Probabilidad : grado de creencia en la certeza de una afirmación. Lo definimos como un rango, entre la certeza total de que algo ocurra y la certeza total de que no ocurra, un rango entre 0 y 1. Se representa P(X) como la probabilidad de que ocurra X, y P(~X) como … Read more
What is probability Probability : degree of belief in the certainty of a statement. We define it as range, between total certainty that something happens, and total certainty that it doesn’t, a range between 0 and 1. It is represented P(X) as the probability that X happens, and P(~X) as a probability that it doesn’t. … Read more
What is Logistic regression? One could say that it is the counterpart of the linear regression model, but adapting the process to classification problems. As we have explained previously, the classification problems, unlike the regression problems, work with target variables that they are categorical, so we enter the terrain of predicting the categorical value of … Read more
This post is intended to be a hardcore mathematicall explanation, as logical and down to earth as possible, of the linear regression algorithm. This will not be the easiest explanation you will find on the internet about linear regression, we will explain all the logic behind the formulas and math inside linear regression. If you … Read more