新創業者資金取得不易，難以向金融機構或投資人融資，時常面臨資金匱乏的問題。隨著科技的進步，群眾募資平台的出現直接連結資金需求者和資金贊助者，籌資難度和耗費成本比傳統融資方式更低，所以近年在各國快速的成長。本研究以台灣最大的群眾募資平台FlyingV作為研究對象，預測與分析群眾募資專案的成敗結果。
本研究運用R語言網路爬蟲的方式，搜集FlyingV平台上，自2012年開站以來，所有類別的募資專案，及可能影響募資成敗的其中各項變數；再用隨機森林演算法，探究募資前、後之各項變數的重要性。研究發現：在募資前，影響成敗結果前3重要變數依序為圖片數、目標金額和回饋方案數；在募資後，影響成敗結果前3重要變數則為更新次數、目標金額和影片觀看數。本研究選取錯誤率最低的決策樹作為預測模型，據以預測分析專案成敗，期望提高群眾募資的成功率。

It is difficult to fund a startup. Entrepreneurs face problems in funding as well as raising capital from financial institutions and investors. Technology progress has witnessed a rise of crowdfunding platforms, which connect demanders of the funds with sponsors, making it an easier and more cost-effective way of funding as compared to the traditional funding approach. Hence there has been a rapid growth across countries. This research studies the largest crowdfunding platform in Taiwan-FlyingV, to analyze its crowdfunding cases and predict whether such cases would succeed or that they would not.
This research adopts R Web Crawler to collect crowdfunding cases and variables possibly affecting the result of each case on the FlyingV platform. Random Forests algorithm is used to discuss the importance of each variable that affects the success or failure, both before and after the funding case. The findings suggest that three important variables prior to the funding process are amount of images, targeted amount of funding, and amount of rewards; after the funding process, the three important variables are amount of updates, targeted amount of funding, and amount of video views. In conclusion, the decision tree with the lowest error rate is used as prediction model to forecast whether a crowdfunding case would succeed, which is expected to raise the success rate of crowdfunding.

Ahlers, Gerrit, Douglas Cumming, Christina Gunther, and Denis Schweizer (2015), “Signaling in Equity Crowdfunding,” Entrepreneurship Theory and Practice, 39 (4), 955-980.
Belleflamme, Paul, Thomas Lambert, and Armin Schwienbacher (2014), “Crowdfunding: Tapping the Right Crowd,” Journal of Business Venturing, 29 (5), 585-609.
Bi, Sheng, Zhiying Liu, and Khalid Usman (2017), “The Influence of Online Information on Investing Decisions of Reward-Based Crowdfunding,” Journal of Business Research, 71 (1), 10-18.
Breiman, Leo (2001), “Random Forests,” Machine Learning, 45 (1), 5-32.
Breiman, Leo, Jerome Friedman, Charles Stone, and R.A. Olshen (1984), “Classification and Regression Trees,” Belmont, CA: Wadsworth International Group.
Bruton, Garry, Susanna Khavul, Donald Siegel, and Mike Wright (2015), “New Financial Alternatives in Seeding Entrepreneurship: Microfinance, Crowdfunding, and Peer to Peer Innovations,” Entrepreneurship Theory and Practice, 39 (1), 9-26.
Calle, Malu, and Victor Urrea (2011), “Letter to the Editor: Stability of Random Forest Importance Measures,” Brief Bioinform, 12 (1), 86-89.
Cholakova, Magdalena, and Bart Clarysse (2015), “Does the Possibility to Make Equity Investments in Crowdfunding Projects Crowd Out Reward Based Investments?” Entrepreneurship Theory and Practice, 39 (1), 145-172.
Cordova, Alessandro, Johanna Dolci, and Gianfranco Gianfrate (2015), “The Determinants of Crowdfunding Success: Evidence from Technology Projects,” Procedia-Social and Behavioral Sciences, 181, 115-124.
Drover, Will, Matthew Wood, and Andrew Zacharakis (2017), “Attributes of Angel and Crowdfunded Investments As Determinants of VC Screening Decisions,” Entrepreneurship Theory and Practice, 41 (3), 323-347.
Ibrahima, Ibrahim, and Tamer Khatib (2017), “A Novel Hybrid Model for Hourly Global Solar Radiation Prediction Using Random Forests Technique and Firefly Algorithm,” Energy Conversion and Management, 138, 413-425.
Kuppuswamy, Venkat, and Barry Bayus (2013), “Crowdfunding Creative Ideas: The Dynamics of Project Backers in Kickstarter,” SSRN Electronic Journal.
Lambert, T, and Schwienbacher A (2010), “An Empirical Analysis of a Crowdfunding,” SSRN Electronic Journal.
Lessmann, Stefan, Bart Baesens, Christophe Mues, and Swantje Pietsch (2008), “Benchmarking Classification Models for Software Defect Prediction: A Proposed Framework and Novel Findings,” IEEE Transactions on Software Engineering, 34 (4), 485-496.
Liao, Chuanhui, Yunhao Zhu, and Xi Liao (2015), “The Role of Internal and External Social Capital in Crowdfunding: Evidence from China,” Revista de Cercetare si Interventie Sociala, 49, 187-204.
Marinic, Igor, Fran Supek, Zrnka Kovacic, Lea Rukavina, Tihana Jendricko, and Dragica Kozaric-Kovacic (2007), “Posttraumatic Stress Disorder: Diagnostic Data Analysis by Data Mining Methodology,” Croatian Medical Journal, 48 (2), 185-197.
Massada, Avi, Alexandra Syphard, Todd Hawbakerc, Susan Stewart, and Volker Radeloffa (2011), “Effects of Ignition Location Models on the Burn Patterns of Simulated Wildfires,” Environmental Modelling & Software, 26 (5), 583-592.
Mollick, Ethan (2013), “The Dynamics of Crowdfunding: Determinants of Success and Failure,” SSRN Electronic Journal, 29 (1).
Mollick, Ethan (2014), “The Dynamics of Crowdfunding: An Exploratory Study,” Journal of Business Venturing, 29 (1), 1-16.
Pierrakis, Yannis, and Liam Collins (2012), “The Venture Crowd: Crowdfunding Equity Investment into Business,” London, UK: NESTA.
Pissarides, Francesca (1999), “Is Lack of Funds the Main Obstacle to Growth? EBRD’s experience with small-and medium-sized businesses in central and eastern Europe,” Journal of Business Venturing, 14(5-6), 519-539.
Rossi, Alberto, Francesco Amaddeo, Marco Sandri, and Michele Tansella (2005), “Determinants of Once-Only Contact in a Community-Based Psychiatric Service,” Social Psychiatry and Psychiatric Epidemiology, 40 (1), 50-56.
Rossi, Matteo (2014), “The New Ways to Raise Capital: an Exploratory Study of Crowdfunding,” International Journal of Financial Research, 5 (2), 8-18.
Schwienbacher, Armin, and Benjamin Larralde (2012), “Crowdfunding of Small Entrepreneurial Ventures,” The Oxford Handbook of Entrepreneurial Finance.
Strobl, Carolin, Anne-Laure Boulesteix, Achim Zeileis, and Torsten Hothorn (2007), “Bias in Random Forest Variable Importance Measures: Illustrations, Sources and a Solution,” BMC Bioinformatics, 8 (1), 25.
Wang, Huazhen, Fan Yang, and Zhiyuan Luo (2016), “An experimental study of the intrinsic stability of random forest variable importance measures,” BMC Bioinformatics, 17 (1), 60.
Xiao, Shengsheng, Xue Tan, Ming Dong, and Jiayin Qi (2014), “How to Design Your Project in the Online Crowdfunding Market? Evidence from Kickstarter,” Proceedings of the Thirty Fifth International Conference on Information Systems, 1-8.
Zheng, Haichao, Dahui Li, Jing Wu, and Yun Xu (2014), “The Role of Multidimensional Social Capital in Crowdfunding: A comparative Study in China and US,” Information & Management, 51 (4), 488-496.
Zheng, Haichao, Jui-Long Hung, Zihao Qi, and Bo Xu (2016), “The Role of Trust Management in Reward-based Crowdfunding,” Online Information Review, 40 (1), 97-118.
Zhou, Mi, Baozhou Lu, Weiguo Fan, and G. Alan Wang (2018), “Project Description and Crowdfunding Success: An Exploratory Study,” Information Systems Frontiers, 20 (2), 259-274.