A Data Science Approach for Predicting Crowdfunding Success

EasyChair Preprint 9430, version 1

Abstract

Crowdfunding is important for backing innovative projects and new startup businesses. However, success in achieving the target fundraising is a big challenge, and it depends on many complex factors. This work uses data science to predict the success of crowdfunding pledges using a historical dataset that was scrapped from the Kickstarter website. The dataset was subject to intensive data wrangling, data exploration, data engineering, and procedures. Four machine learning models were constructed in this study using four algorithms: (1) Random Forests (RF), (3) K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The models were trained using a separate portion that makes up two-thirds of the dataset, while the remaining third was used to evaluate the models. The KNN model achieved the best performance with a classification accuracy of 97.9% and an AUC of 98.3%. The Random Forests model achieved the second-best performance with a classification accuracy of 94.9% and an AUC of 98.9%. The Precision, Recall, F1, and AUC metrics also confirmed the validity of the reported results, while the confusion matrix and the ROC curve also confirmed the robustness of the constructed models.

Keyphrases: Crowdfunding, Data Mining, Data Science, Fundraising, Kickstarter, machine learning

@booklet{EasyChair:9430,
  author    = {Ahmed Banimustafa and Sattam Almatarneh and Olla Bulkrock and Ghassan Samara and Mohammad Aljaidi},
  title     = {A Data Science Approach for Predicting Crowdfunding Success},
  howpublished = {EasyChair Preprint 9430},
  year      = {EasyChair, 2022}}