A common phenomenon that increasingly stimulates the interest of investors, companies, and entrepreneurs involved in crowd funding activities particularly on the Kickstarter website is identifying metrics that make such campaigns markedly successful. This study seeks to gauge the importance of key predictive variables or features based on statistical analysis, identify model-based machine learning methods based on performance assessment that predict success of a campaigns, and compare the selected different machine learning algorithms. To achieve our research objectives and maximize insight into the dataset used, feature engineering was performed. Then, machine learning models, inclusive of Logistic Regression (LR), Support Vector Machines (SVMs) in the form of Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and random forest analysis (bagging and boosting), were performed and compared via cross validation approaches in terms of their resulting test error rates, F1 score, Accuracy, Precision, and Recall rates. Of the machine learning models employed for predictive analysis, the test error rates and the other classification metric scores obtained across the three cross-validation approaches identified bagging and gradient boosting (the SVMs) as more robust methods for predicting success of Kickstarter projects. The major research objectives in this paper have been achieved by accessing the performance of key statistical learning methods that guides the choice of learning methods or models and giving us a measure of the quality of the ultimately chosen model. However, Bayesian semiparametric approaches are of future research consideration. These methods facilitate the usage of an infinite number of parameters to capture information regarding the underlying distributions of even more complex data.

Background Although evidence on healthcare utilization avoidance during COVID-19 pandemic is emerging, such knowledge is limited in rural settings. An effective policy to the COVID-19 shocks and stresses in rural settings require empirical evidence to inform the design of health policies and programmes. To help overcome this evidence gap and also contribute to policy decisions, this study aimed at examining COVID-19-induced healthcare utilization avoidance and associated factors in rural India. Methods This study used the third-round data from the COVID-19-Related Shocks in Rural India survey conducted between 20-24 September, 2020 across six states. The outcome variable considered in this study was COVID-19-induced healthcare utilization avoidance. Multivariable Binary Logistic Regression Model via Multiple Imputation was used to assess the factors influencing COVID-19-induced healthcare utilization avoidance. Results Data on 4,682 respondents were used in the study. Of this, the prevalence of COVID-19-induced healthcare utilization avoidance was 15.5% in rural India across the six states. After adjusting for relevant covariates, participants from the Bihar State have significantly higher likelihood of COVID-19-induced healthcare utilization avoidance compared to those from the Andhra Pradesh. Also, participants whose educational level exceeds high school, those who use government hospital/clinic, engage in daily wage labour in agriculture have significantly higher odds of COVID-19-induced healthcare utilization avoidance compared to their counterparts. Conclusion Our study revealed that state of residence, type of health facility used, primary work activity and educational level were associated with COVID-19-induced healthcare utilization avoidance in rural India. The findings suggest that policy makers and public health authorities need to formulate policies and design interventions that acknowledge socioeconomic and demographic factors that influence healthcare use avoidance.