Financial institutions use credit scoring to assess borrowers' potential default risk. In recent years, many lenders have realized the good potential of borrowers with little or no financial history and are looking to use alternative data types to compensate for the lack of credit history data to calculate the probability of default and credit score. This research seeks to investigate the effect of variables and data related to people's social network on their credit score. Achieving the above goals is done by finding meaningful information about people's social data to measure how such data affects their credit score. The basic principle of this research is that people with a high credit score have social relationships with people of the same age. In this research, a data set of over 300,000 loans paid by an Iranian bank to real people has been used to verify and explain the effects of social network features on credit scores. The results of the studies conducted using the logistic regression method show that, statistically, people's social variables can predict the probability of their loan default. The results of machine learning algorithms also show that social network information can significantly improve the performance of loan default prediction.
