Estimating the Days to Success of Campaigns in Crowdfunding: A Deep Survival Perspective

Abstract

Crowdfunding is an emerging mechanism for entrepreneurs or individuals to solicit funding from the public for their creative ideas. However, in these platforms, quite a large proportion of campaigns (projects) fail to raise enough money of backers’ supports by the declared expiration date. Actually, it is very urgent to predict the exact success time of campaigns. But this problem has not been well explored due to a series of domain and technical challenges. In this paper, we notice the implicit factor of distribution of backing behaviors has a positive impact on estimating the success time of the campaign. Therefore, we present a focused study on predicting two specific tasks, i.e., backing distribution prediction and success time prediction of campaigns. Specifically, we propose a Seq2seq based model with Multi-facet Priors (SMP), which can integrate heterogeneous features to jointly model the backing distribution and success time. Additionally, to keep the change of backing distributions more smooth as the backing behaviors increases, we develop a linear evolutionary prior for backing distribution prediction. Furthermore, due to high failure rate, the success time of most campaigns is unobservable. We model this censoring phenomenon from the survival analysis perspective and also develop a non-increasing prior and a partial prior for success time prediction. Finally, we conduct extensive experiments on a real-world dataset from Indiegogo. Experimental results clearly validate the effectiveness of SMP.

Promotion of Answer Value Measurement With Domain Effects in Community Question Answering Systems

“…Recently, with the development of deep learning, scholars proposed some neural network-based models to explore the semantic relations of Q&A texts [35], [36], which achieved great success on measuring answer quality [3], [4], [37]. Despite the deep belief networks (DBNs) [38] and recursive neural networks [39] have shown some nonlinear fitting capability, the great success of convolutional neural networks (CNNs) [40]- [42] and recurrent neural networks (RNNs) [43]- [45] on various tasks completely changed the research direction. For example, Severyn and Moschitti [3] employed a CNN to generate a representation for each sentence and then used similarity matrix to compute a relevant score.…”

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

“…The research of online crowdfunding can be divided into two categories according to the research perspective: for the individual projects and for the entire market. For the individual projects, most researchers paid much attention to the prediction of project success (Li, Rakesh, and Reddy 2016;Jin et al 2019). Besides, Liu et al (2017) optimized the algorithm of production supply to reduce the redundant losses of creators, and Zhao et al (2017b) focused on tracking the dynamics for projects in their complete funding durations.…”

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

“…• VAR (Vector Autoregression) (Sims 1980) (Jin et al 2019) is a variant of Seq2Seq model that using an encoder to track the history dynamics and a decoder to predict the future dynamics, along with the monotonously increasing prior. • TC3 is our proposed basic model to utilize actor-critic architecture to simulate decision-making process between investors and campaigns.…”

“…Some methods have been explored in the literature, including hierarchical regression (Zhao et al 2017b) and basis-synthesis techniques (Ren et al 2018). Moreover, others turn to predict the backing distribution of campaigns through a Seq2Seq framework (Jin et al 2019). However, there are still challenges on funding process modeling and series pattern utilization.…”