Save optimal bins and/or splits points and transformation depending on the target type.
This is handy to implement binning transformation with other languages (e.g., SAS). Only a JSON parser is required to produce a set of if-else to transform original data.
Implementation of Genetic Algorithm for feature selection of neural networks proposed by Genetic algorithm-based heuristic for feature selection in credit risk assessment paper.
openLGD is a Python powered library for the statistical estimation of Credit Risk Loss Given Default models. It can be used both as standalone library and in a federated learning context where data remain in distinct (separate) servers
Project which will predict credit default or credit risk using artificial neural network algorithms. It will help banks and financial institutions to assign a credit score to the customer profile/portfolio and make a decision whether to sanction a loan or not