Tools
Tools
Teotia, Ashwani (2019) Prediction of Crowdfunding Project Success Probability using Machine Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (956kB) | Preview |
Preview |
PDF (Configuration manual)
Download (914kB) | Preview |
Abstract
Crowd markets have established as alternative financing means where the borrowers preserve funding from the crowd in small increments. However, crowd markets mainly reward-based crowd markets are facing the problem of very low project success rate. Consequently, it's leading to low revenues for platforms and the project creators are challenged to meet fund targets. These problems are due to lack of project optimization tools for project creators. This research will contribute academically to establish a research area to provide a solution in terms of probability of success of crowd markets projects and on the other hand will act as a foundational work for practitioners to optimize project success decisioning systems.This research is evaluating the predictive accuracy of probability predicted by the machine learning models. Support vector machine (SVM), k-nearest neighbors (k-NN) and Random forest are used to predict probability. Sorting smoothing method (SSM) is used to predict the estimated actual probability. Linear regression is used to evaluate the relation between predicted probability and the estimated actual probability. Probability is the better parameter to provide project success insights facilitating borrowers for the decision making, increased revenue for the platform and increased transparency for the funders. Results of this research found random forest model have the highest predictive accuracy as (R-Squared=0.93) in predicting the probability of the success of the project and would be used to build decisioning systems.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems H Social Sciences > HG Finance > Investment > Investment Strategy |
| Divisions: | School of Computing > Master of Science in FinTech |
| Depositing User: | Dan English |
| Date Deposited: | 02 Jun 2020 10:42 |
| Last Modified: | 02 Jun 2020 10:42 |
| URI: | https://norma.ncirl.ie/id/eprint/4216 |
Actions (login required)
 |
View Item |