Prediction of the Importance of Factors Influencing Co-sharing Attitudes Using Machine Learning

The sharing economy concept has been gaining importance in recent years. It promotes environmentally friendly practices. A growing group of consumers values access to goods or services more than ownership, leading to better use of resources. Getting information on factors influencing co-sharing attitudes is essential for market competition. As the most common marketing research method is a survey and the survey response rate is lowering, machine learning methods may be employed to predict factors importance based on a sample of previous research results. The aim of the research was to determine the possibility of classifying co-sharing survey respondents depending on their method of assessing each decision-making factor separately using selected machine learning methods. XGBoost, decision trees, and LightGBM models were used. The input data were the respondents’ characteristics, and the output data was the importance of eight factors in the co-sharing decision-making process. The accuracy of built models was the highest for sharing preference using all three methods: LightGBM (0.715), decision trees (0.704), and XGBoost (0.660). Considering the accuracy for all the factors, the most suitable method was decision trees (mean 0.551) and the worst XGBoost (mean 0.484). The presented research shows that there is a possibility of predicting the importance of decision-making factors based on respondents’ characteristics. The research results may be essential for smaller companies that do not have the funds or time to take extensive market surveys.