Programma
Login

Nowcasting financial crisis with deep learning techniques

In this tutorial, I’ll show how train machine learning models to predict a financial crisis event in the next 20 days. Specifically, we’ll speak about:

  • preparation of the dataset
  • selection of variables with RandonForest and Boruta
  • training and the predictions
  • measure of our performances

Abstract

This tutorial shows how apply Regression Models and Deep Learning Models to nowcasting stock markets crisis events. Specifically, we’ll how the transmission mechanisms across stock markets can be used to train machine learning models to predict crisis events. The tutorial’ll show the entire pipeline: from the preparation of the dataset, how balance observations and how measure our performances. Here the git repo of the talk: https://github.com/mauropelucchi/pyconit2022

Speaker
Pelucchi Mauro
Argomento
PyData
Livello audience
Intermediate
Lingua
Inglese
Durata
30 minuti
Speaker name:
Pelucchi Mauro
Torna al programma
      Powered by Vercel Logo