Print Email Facebook Twitter SME Credit Scoring Using Social Media Data Title SME Credit Scoring Using Social Media Data Author Septian Gilang Permana Putra, Septian (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Web Information Systems) Contributor Bozzon, Alessandro (mentor) Redi, J.A. (mentor) Degree granting institution Delft University of Technology Date 2018-09-25 Abstract Credit analysis is required in a wide variety of decision of a modern economy.It includes understanding the credit risk of small-medium enterprises (SMEs),which today is the most significant contributor to the economy of almost everynation. Creditors usually use credit scoring as a tool to predict the probability ofthe SMEs to default in the future. The existing methods of SMEs credit scoringstill rely on traditional data, which may require high cost and have low scalability.This thesis proposed an alternative approach of credit scoring for small-mediumenterprises (SMEs), which incorporate a novel set of features extracted from socialmedia data.As a study case, we generate the credit scoring dataset which contains 20traditional features and 35 social media features to quantify the creditworthinessof more than 20,000 SMEs. The social media features are formulated basedon the previous studies in the adoption of social media data for personal creditscoring and the social media metrics for quantifying business social perception.To build the dataset, we develop the method to collect the information from somepublic websites and SMEs’ Facebook page.We conduct some experiments to develop credit scoring model for SMEs.We found that using only the social media features insufficient to model SMEsdefault in the future. However, by combining both social media features to buildthe credit scoring model, we will get better performance compared to the modeldeveloped using only traditional data. Subject Credit ScoringSocial MediaSMEsLogistic regressionXGBoostdefault classification To reference this document use: http://resolver.tudelft.nl/uuid:c13e9430-9118-495c-9b36-2c6407ee8401 Part of collection Student theses Document type master thesis Rights © 2018 Septian Septian Gilang Permana Putra Files PDF SME_Credit_Scoring_Using_ ... a_Data.pdf 3.93 MB Close viewer /islandora/object/uuid:c13e9430-9118-495c-9b36-2c6407ee8401/datastream/OBJ/view