Machine Learning approach for Credit Scoring

In this work we build a stack of machine learning models aimed at composing a state-of-the-art credit rating and default prediction system, obtaining excellent out-of-sample performances. Our approach is an excursion through the most recent ML / AI concepts, starting from natural language processes (NLP) applied to economic sectors' (textual) descriptions using <PRE_TAG>embedding</POST_TAG> and <PRE_TAG>autoencoders</POST_TAG> (AE), going through the classification of defaultable firms on the base of a wide range of economic features using <PRE_TAG>gradient boosting machines</POST_TAG> (GBM) and calibrating their probabilities paying due attention to the treatment of unbalanced samples. Finally we assign credit ratings through genetic algorithms (<PRE_TAG>differential evolution</POST_TAG>, DE). Model interpretability is achieved by implementing recent techniques such as <PRE_TAG>SHAP</POST_TAG> and <PRE_TAG>LIME</POST_TAG>, which explain predictions locally in features' space.