Risk assessment model in kickstarter campaigns using machine learning

Authors

DOI:

https://doi.org/10.22279/navus.2019.v9n4.p66-79.914

Keywords:

Risk Assessment. Kickstarter. Machine Learning. Crowdfunding.

Abstract

Crowdfunding has become a virtual phenomenon because it is a business model that aims to raise funds for collective projects of various kinds. Risk Assessment based on the characteristics of such projects is an important step in minimizing financial losses. In this sense, the objective of this work is to present a model for risk assessment in these projects using Statistical and Machine Learning (ML) techniques, considering the stages of preparation, processing and analysis of the results. For the development of the work the WEKA tool and the Python programming language with ML specific modules were used. The research showed that the use of ML techniques was efficient, obtaining an accuracy of 77%, higher to the 76% of the model proposed by Etter, Grossglauser e Thiran (2013) and can therefore be used as a method in Risk Assessment in Kickstarter Campaigns, providing conditions for investors to mitigate the risks associated with projects of this nature by analyzing graphs and numerical data.

Downloads

Download data is not yet available.

Author Biographies

Gustavo Peixinho Cardoso, Universidade Nove de Julho - UNINOVE

Estudante de graduação no curso de Ciências da Computação.

Bruno Guimarães Sininbardi, Universidade Nove de Julho - UNINOVE

Estudante de graduação no curso de Ciências da Computação.

Murilo Silva Sobral, Universidade Nove de Julho - UNINOVE

Estudante de graduação no curso de Ciências da Computação.

Edson Melo de Souza, Universidade Nove de Julho - UNINOVE

PhD candidate in Informatic and Knowledge Management. Master in Production Engineering with emphasis on Machining Process Management Technologies (2013). He holds a specialization in Strategic Business Management (2009), extension in Teaching Practices for Higher Education (2009) and graduation in Computer Science (2006), both by the University of Nove de Julho (UNINOVE). He is currently a professor at Universidade Nove de Julho (UNINOVE), where he teaches subjects related to Computer Science, Information Systems and Technologies in the area of computing. He has experience in Computer Science, Information Systems and Information Technology with emphasis on Algorithms, Modeling and Simulation, Artificial Intelligence, Computational Vision, Signal Processing, Database and Java Language. Works in the development of applications for Desktop, Web, Mobile, Embedded and IoT (Internet of Things) environments. Promotes scientific initiation research in the area of Artificial Intelligence.

References

BHASKARAN, Subhashini; LU, Kevin; AALI, Al Mansoor. Student Performance and Time-To-Degree Analysis Using J48 Decision Tree Algorithm. In: Managing Intellectual Capital and Innovation for Sustainable and Inclusive Society: Managing Intellectual Capital and Innovation, 2015, Bari. Proceedings of the MakeLearn and TIIM Joint International Conference 2. Bari: ToKnowPress, 2015. p. 2029-2029. Disponível em: https://ideas.repec.org/h/tkp/mklp15/2029.html. Acesso em: 14 jul. 2019.

BITTENCOURT, Hélio Radke. Regressão logística politômica: revisão teórica e aplicações. Acta Scientiae, v. 5, n. 1, p. 77–86, 2003.

BOUMAN, Roland; VAN DONGEN, Jos. Pentaho Solutions: Business Intelligence and Data Warehousing with Pentaho and MySQL. Indianapolis, Indiana: Wiley Publishing, 2009.

BRUTON, Garry et al. New financial alternatives in seeding entrepreneurship: Microfinance, crowdfunding, and peer-to-peer innovations. Entrepreneurship: Theory and Practice, v. 39, n. 1, p. 9–26, 2015.

COCATE, F. M. Flávia Medeiros; PERNISA JÚNIOR, Carlos. Estudo sobre crowdfunding: fenômeno virtual em que o apoio de uns se torna a força de muitos. In: SIMPÓSIO NACIONAL ABCiber, 5., 2011, Florianópolis. Anais [...]. Florianópolis: UDESC/UFSC, 2011. p. 1-14. Disponível em: http://abciber.org.br/simposio2011/anais/Trabalhos/artigos/Eixo%206/17.E6/226-353-1-RV.pdf. Acesso em: 11 jul. 2019.

DRESNER, Steven. System and Method of Data Collection, Analysis and Distribution. U.S. Patent Application, US 2013/0185228 A1, n. 19, filed July 18, 2013. v. 1, p. 1-28, 2013. Disponível em: https://patentimages.storage.googleapis.com/66/a5/ab/e5529cbc15e6ae/US20130185228A1.pdf. Acesso em: 14 jul. 2019.

ETEMAD, Hamid. The emergence of online global market place and the multilayered view of international entrepreneurship. Journal of International Entrepreneurship, v. 15, n. 4, p. 353–365, 2017.

ETTER, Vincent; GROSSGLAUSER, Matthias; THIRAN, Patrick. Launch hard or go home! Predicting the Success of Kickstarter Campaigns. In: THE FIRST ACM CONFERENCE ON ONLINE SOCIAL NETWORKS (COSN'13), 2013, Boston. Proceedings of the First ACM conference on Online Social Networks (COSN'13). Boston: ACM, 2013. p. 177-182. Disponível em: https://infoscience.epfl.ch/record/189675. Acesso em: 14 jul. 2019.

FRIEDMAN, Jerome H. Greedy Function Approximation: a Gradient Boosting Machine. The Annals of Statistics, v. 29, n. 5, p. 1189–1232, 2018.

GROSSMAN, Maura R.; CORMACK, Gordon V. Grossman-cormack glossary of technology-assisted review, the. Fed. Cts. L. Rev., v. 7, p. 85, 2014.

HARRIS, Michael. Feature Engineering for Algorithmic and Machine Learning Trading. [2017]. Disponível em: https://medium.com/@mikeharrisNY/feature-engineering-for-algorithmic-and-machine-learning-trading-d0326305ac7b. Acesso em: 20 jan. 2019.

KICKSTARTER (EUA) (ed.). About Kickstarter. 2019. Disponível em: https://www.kickstarter.com. Acesso em: 20 jan. 2019.

KIM, Keongtae et al. Information Disclosure and Crowdfunding: An Empirical Analysis of the Disclosure of Project Risk. Academy of Management Proceedings, v. 2017, n. 1, p. 12360, 1 jan. 2017.

KUPPUSWAMY, Venkat; BAYUS, Barry L. Crowdfunding Creative Ideas: The Dynamics of Project Backers in Kickstarter. [2018]. Disponível em: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2234765. Acesso em: 20 jan. 2019.

LI, Yan; RAKESH, Vineeth; REDDY, Chandan K. Project success prediction in crowdfunding environments. In: WSDM '16, 2016, San Francisco. Proceedings of the Ninth ACM International Conference on Web Search and Data Mining. New York: ACM, 2016. p. 247-256. Disponível em: https://dl.acm.org/citation.cfm?id=2835791. Acesso em: 14 jul. 2019.

LICHTENBERG, Frank R. Entrepreneurial Risk-Taking in Crowdfunding Campaigns. Small Bus Econ. January, p. 843–859, 2011.

LILLEBERG, Joseph; ZHU, Yun; ZHANG, Yanqing. Support vector machines and word2vec for text classification with semantic features. In: COGNITIVE INFORMATICS AND COGNITIVE COMPUTING, 2015, Beijing. Proceedings of the 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC). Beijing: IEEE, 2015. p. 136-140. Disponível em: https://ieeexplore.ieee.org/abstract/document/7259377. Acesso em: 14 jul. 2019.

MAROM, Dan; ROBB, Alicia; SADE, Orly. Gender dynamics in crowdfunding (Kickstarter): Deals, and taste-based discrimination. NBER working papers, n. 430, p. 1–75, 2016.

MAYRINK, Victor; HIPPERT, Henrique S. A hybrid method using Exponential Smoothing and Gradient Boosting for electrical short-term load forecasting. In: LATIN AMERICA CONGRESS ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2016, Cartagena. Proceedings of the 2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI). Cartagena: IEEE, 2016. p. 1-6. Disponível em: https://ieeexplore.ieee.org/abstract/document/7885697. Acesso em: 14 jul. 2019.

MENDONÇA, Rafael Uttempergher de; MACHADO, Luiz Henrique Mourão. Análise do crowdfunding no empreendedorismo brasileiro – características e tendências. South American Development Society Journal, v. 1, n. 3, p. 37–53, 2015.

NASCIMENTO JUNIOR, Luiz Antônio Ferreira. Aplicando método do gradiente ótimo na otimização do cálculo do grau de cobertura das regras em árvores de decisão Fuzzy. Revista Brasileira de Computação Aplicada, v. 9, n. 3, p. 31-43, 2017.

OLIVEIRA, Paulo Lima Júnior; GONZAGA, Luiz de Castro Júnior; LUIZ ZAMBALDE, Andreé Luiz. Applying Textmining to Classify News About Supply and Demand in the Coffee Market. IEEE Latin America Transactions, v. 14, n. 12, p. 4768–4774, 2016.

PIECH, C. et al. Deep Knowledge Tracing. In: CORTES, C.; LAWRENCE, N. D.; LEE, D. D.; SUGIYAMA, M.; GARNETT, R. (Eds.). Advances in Neural Information Processing Systems 28. Montreal: Curran Associates, Inc., 2015. p. 505–513.

QIU, Calvin. Issues in Crowdfunding: Theoretical and Empirical Investigation on Kickstarter. SSRN Electronic Journal, 2013. Disponível em: http://www.ssrn.com/abstract=2345872. Acesso em: 1 jul. 2019.

RUBIANO, Sandra Milena Merchan; GARCIA, Jorge Alberto Duarte. Analysis of Data Mining Techniques for Constructing a Predictive Model for Academic Performance. IEEE Latin America Transactions, v. 14, n. 6, p. 2783–2788, 2016.

SALZBERG, Steven L. C4. 5: Programs for machine learning by J. Ross Quinlan Morgan Kaufmann Publishers, Inc., 1993. Machine Learning, v. 16, n. 3, p. 235-240, 1994.

SAMANCI, Murat; KISS, Gabor. Exploratory Study on Technology related Successfully Funded Crowdfunding Projects. Post Online Market Presence. 2014. 44 f. Master Thesis (Entrepreneurship), Department of Business Administration, Lunds University, Lund, 2014.

SELVAKUBERAN, K; INDRADEVI, M; RAJARAM, R. Combined Feature Selection and classification – A novel approach for the categorization of web pages. UK Journal of Information and Computing Science, v. 3, n. 2, p. 83–89, 2008.

SIMON, Phil. Too big to ignore: the business case for big data. Roboken, New Jersey: John Wiley & Sons, 2013. 256 p.

SILVA, Italla Dayanna da et al. Non-Stationary Demand Forecasting Based on Empirical Mode Decomposition and Support Vector Machines. IEEE Latin America Transactions, v. 15, n. 9, p. 1785–1792, 2017.

VALIATI, Vanessa Amália Dalpizol; TIETZMANN, Roberto. Crowdfunding: O Financiamento Coletivo como Mecanismo de Fomento à Produção Audiovisual. In: CONGRESSO DE CIÊNCIAS DA COMUNICAÇÃO NA REGIÃO SUL, 13., 2012, Chapecó. Anais... Chapecó: Pontifícia Universidade Católica do Rio Grande do Sul, 2012. v. 2, n. 6, p. 1-13. Disponível em: http://www.intercom.org.br/papers/regionais/sul2012/resumos/R30-1090-1.pdf. Acesso em: 14 jul. 2019.

YOUNG, Tom et al. Recent trends in deep learning based natural language processing [Review Article]. IEEE Computational Intelligence Magazine, v. 13, n. 3, p. 55–75, 2018.

ZHU, Huasheng; ZHOU, Zach Zhizhong. Analysis and outlook of applications of blockchain technology to equity crowdfunding in China. Financial Innovation, v. 2, n. 1, p. 29, 2016.

Published

2019-10-01

Issue

Section

Articles