The cooperation and contamination among mathematicians, statisticians and econometricians working in actuarial sciences and finance are improving the research on these topics and producing numerous meaningful scientific results. This volume presents new ideas in the form of four- to six-page papers presented at the International Conference MAF2022 - Mathematical and Statistical Methods for Actuarial Sciences and Finance. Due to the COVID-19 pandemic, the conference, to which this book is related, was organized in a hybrid form by the Department of Economics and Statistics of the University of Salerno, with the partnership of the Department of Economics of Cà Foscari University of Venice, and was held from 20 to 22 April 2022 in Salerno (Italy)

MAF2022 is the tenth edition of an international biennial series of scientific meetings, started in 2004 on the initiative of the Department of Economics and Statistics of the University of Salerno. It has established itself internationally with gradual and continuous growth and scientific enrichment. The effectiveness of this idea has been proven by the wide participation in all the editions, which have been held in Salerno (2004, 2006, 2010, 2014, 2022), Venice (2008, 2012 and 2020 online), Paris (2016) and Madrid (2018).

This book covers a wide variety of subjects: artificial intelligence and machine learning in finance and insurance, behavioural finance, credit risk methods and models, dynamic optimization in finance, financial data analytics, forecasting dynamics of actuarial and financial phenomena, foreign exchange markets, insurance models, interest rate models, longevity risk, models and methods for financial time series analysis, multivariate techniques for financial markets analysis, pension systems, portfolio selection and management, real-world finance, risk analysis and management, trading systems, and others.

This volume is a valuable resource for academics, PhD students, practitioners, professionals and researchers. Moreover, it is also of interest to other readers with quantitative background knowledge.