Analyzing factors that influence customer decision on buying second-hand products from online platforms

The increasing use of online mobile applications and websites for shopping, coupled with the rising popularity of second-hand product consumption, has transformed the way consumers engage in retail transactions. This master's thesis investigates the motivations and factors influencing individuals' participation in online second-hand shopping. Based on existing scholarly literature, the impact of users' internet habits and e-commerce use on their engagement in second-hand shopping are examined. Factors obtained as a result of literature review and thought to be effective on people's second hand shopping behaviors are determined as technical convenience of platform, personal choices of users, trust in the product and the vendor, situational factors including physical environments and temporal considerations, users' environmental awareness, hygiene-related issues, and social environment of user. The research methodology encompasses data collection, preprocessing, and creating a predictive model to predict user behaviour on online second-hand shopping decision. Models were trained using various machine learning methods such as Logistic Regression, Decision Tree Algorithm, Random Forest Algorithm, Xgboost Algorithm and Artificial Neural Networks. At the end of the study, it is emphasized that the technical features of the application used and location-based price changes have a decisive effect on user behavior. The findings provide insights into influential features affecting usage habits and offer recommendations for future research. Overall, this study contributes to understanding the complex dynamics of online second-hand shopping and provides valuable insights for both researchers and practitioners in the field of e-commerce and consumer behavior.