The paper presents two algorithms as a solution to the problem of identifying fraud intentions of a customer. Their purpose is to generate variables that contribute to fraud models’ predictive power improvement. In this article, a novel approach to the feature engineering, based on anomaly detection, is presented. As the choice of statistical model used in the research improves predictive capabilities of a solution to some extent, most of the attention should be paid to the choice of proper predictors. The main finding of the research is that model enrichment with additional predictors leads to the further improvement of predictive power and better interpretability of anti-fraud model. The paper is a contribution to the fraud prediction problem but the method presented may generate variable input to every tool equipped with variableselection algorithm. The cost is the increased complexity of the models obtained. The approach is illustrated on a dataset from one of the European banks.

The purpose of this paper is to compare two approaches applied in property valuation: artificial neural networks and spatial regression. Despite the fact that artificial neural networks are often the first choice for modeling in the big data era, spatial econometrics methods offer incorporation of information on dependences between multiple objects in the studied space. Although this dependency structure can be incorporated into artificial neural network via feature engineering, this study is focused on abilities of reproducing it with machine learning method from crude coordinate data. The research is based on the database of 18,166 property sale transactions in Warsaw, Poland. According to this study, such volume of data does not allow artificial neural networks to compete in reflecting spatial dependence structure with spatial regression models.