Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model

Abstract

Well begun is half done. In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms. However, estimating the early fundraising performance before the project published is very challenging and still under-explored. To that end, in this paper, we present a focused study on this important problem in a market modeling view. Specifically, we propose a Graphbased Market Environment model (GME) for estimating the early fundraising performance of the target project by exploiting the market environment. In addition, we discriminatively model the market competition and market evolution by designing two graph-based neural network architectures and incorporating them into the joint optimization stage. Finally, we conduct extensive experiments on the real-world crowdfunding data collected from Indiegogo.com. The experimental results clearly demonstrate the effectiveness of our proposed model for modeling and estimating the early fundraising performance of the target project.

Learning the Compositional Visual Coherence for Complementary Recommendations

“…Recently, many researchers utilized deep learning methods to generate item recommendations [Kang et al, 2017]. To further explore item visual contents, some studies developed deep neural networks to extract the aesthetic information of images Yu et al, 2018]. Although various researches have leveraged visual features in recommendation tasks, they usually treated item visual features as side information and the item visual relations have been largely unexploited.…”

“…For enhancing the recommendations, explicitly modeling the complex relations among items under domain-specific applications is an indispensable part . Along this line, many researchers focused on exploring the item combination-effect relations, such as substitutable relations [McAuley et al, 2015a;McAuley et al, 2015b] and complementary relations [Rudolph et al, 2016;Yu et al, 2019]. For a long time, many researchers mainly utilized unsupervised learning methods to explore co-occurrence relations for complementary recommendations [Tan et al, 2004;Zheng et al, 2009].…”

“…For a long time, many researchers mainly utilized unsupervised learning methods to explore co-occurrence relations for complementary recommendations [Tan et al, 2004;Zheng et al, 2009]. Recently, more and more studies based on supervised approaches were proposed to model complementary relationships, which were mainly reflected by users' purchases of the complements or item content similarities [McAuley et al, 2015a;Zhang et al, 2018]. Along this line, since natural complementary relationships in the fashion items Lo et al, 2019], there was a particular interest in understanding the compatibility [Song et al, 2017; of fashion items to generate complementary recommendations [Han et al, 2017;Hsiao and Grauman, 2018;Vasileva et al, 2018].…”

“…For enhancing user satisfaction and recommendation performances, it is an indispensable part to understand how products relate to each other in recommender systems [McAuley et al, 2015a;. Along this line, complementary recommendations [Yu et al, 2019], which aim at exploring item compatible associations to enhance the qualities of each item or * Corresponding Author. another, have become a hot topic in both academia and industry in recent years.…”