Financial institutions and regulators increasingly rely on large-scale data analysis, particularly machine learning, for credit decisions. This paper assesses ten machine learning algorithms using a dataset of over 2.5 million observations from a financial institution. We also summarize key statistical and machine learning models in credit scoring and review current research findings. Our results indicate that ensemble models, particularly XGBoost, outperform traditional algorithms such as logistic regression in credit classification. Researchers and experts in the subject of credit risk can use this work as a practical reference as it covers crucial phases of data processing, exploratory data analysis, modeling, and evaluation metrics.

Investors seem to hold on to their losing stocks to a greater extent than they hold on to their winning stocks. This well-documented behavioural regularity is termed disposition effect (Shefrin and Statman, 1985). We set an experiment to replicate results from a previous study of the disposition effect (Weber and Camerer, 1998) and further show that a subject's gender may interfere with the effect's detection.

Financial economists usually assess market efficiency in absolute terms. This is to be viewed as a shortcoming. One way of dealing with the relative efficiency of markets is to resort to the efficiency interpretation provided by algorithmic complexity theory. We employ such an approach in order to rank 36 stock exchanges and 20 US dollar exchange rates in terms of their relative efficiency.

Editorial: Highlights in psychology: cognitive bias