Neural network as challenger in classification tasks

Original by DataQuest, 2017, 6 pages

This summary note was posted on 21 July 2018, by Reinie in Credit risk #neural network, #python

Can use single neuron to do logistic regression (use logit as a smooth function)
Use python’s Kera package (keras.io)
Challenge model with a small neural network of two connected hidden layers with each 10 neurons
Identify possible non linearities by looking at default rate occurrence per driver
Examine gini as a function of driver threshold
For bigger datasets use Python Theano or Tensorflow

Latest Hamster Notes

Start with Why posted in Management #innovation, #Why
4 steps to optimise product value posted in Agile Management #agile, #product, #Scrum, #value
5 paradoxes of digital business leadership posted in Agile #agile, #leadership, #value
Product Vision, 10 tips posted in Agile #agile, #product, #Scrum
Progress in adopting the Principles for effective risk data aggregation and risk reporting 2023 posted in Credit risk Finance #BIS, #data, #reporting
Leadership styles by ChatGPT posted in Management #ChatGPT, #leadership, #style
Gen AI round table posted in Machine Learning #ChatGPT, #Copilot, #Gen AI, #Github
Leadership in fully remote teams posted in Management #leader, #leadership, #remote, #thatconference19
Leadership for the reluctant leader posted in Management #leader, #leadership, #thatconference19
Corporate Credit Risk Modelling and the Macroeconomy posted in Finance #corporate, #duration, #macroeconomy