Saltar al contenido

Introducción a las cadenas de Markov

septiembre 21, 2021
1jcbUF7dAhAIRS8nfUlNtow

Introducción a las cadenas de Markov

¿Qué son las cadenas de Markov, cuándo usarlas y cómo funcionan?

Devin Soni 👑

5 de marzo de 2018·4 min de lectura

1*jcbUF7dAhAIRS8nfUlNtow
(Generado a partir de http://setosa.io/ev/markov-chains/)

Guión

Imagine that there were two possible states for weather: sunny or cloudy. You can always directly observe the current weather state, and it is guaranteed to always be one of the two aforementioned states.Now, you decide you want to be able to predict what the weather will be like tomorrow. Intuitively, you assume that there is an inherent transition in this process, in that the current weather has some bearing on what the next day’s weather will be. So, being the dedicated person that you are, you collect weather data over several years, and calculate that the chance of a sunny day occurring after a cloudy day is 0.25. You also note that, by extension, the chance of a cloudy day occurring after a cloudy day must be 0.75, since there are only two possible states.You can now use this distribution to predict weather for days to come, based on what the current weather state is at the time.

Una visualización del ejemplo del tiempo.

El modelo

1*oqBd8eLkXyU h0AhV m73w

Vista general de una cadena de Markov de muestra, con estados como círculos y aristas como transiciones

Matriz de transición de muestra con 3 estados posibles
1*y8ZkBHQm4D9rF3Bl ok9 w

Vector de estado inicial con 4 estados posibles

Conclusión

close