skip to main content

Title: Modeling Menu Bundle Designs of Crowdfunding Projects
Offering products in the forms of menu bundles is a common practice in marketing to attract customers and maximize revenues. In crowdfunding platforms such as Kickstarter, rewards also play an important part in influencing project success. Designing rewards consisting of the appropriate items is a challenging yet crucial task for the project creators. However, prior research has not considered the strategies project creators take to offer and bundle the rewards, making it hard to study the impact of reward designs on project success. In this paper, we raise a novel research question: understanding project creators’ decisions of reward designs to level their chance to succeed. We approach this by modeling the design behavior of project creators, and identifying the behaviors that lead to project success. We propose a probabilistic generative model, Menu-Offering-Bundle (MOB) model, to capture the offering and bundling decisions of project creators based on collected data of 14K crowdfunding projects and their 149K reward bundles across a half-year period. Our proposed model is shown to capture the offering and bundling topics, outperform the baselines in predicting reward designs.We also find that the learned offering and bundling topics carry distinguishable meanings and provide insights of key factors on project success.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the 2017 ACM on Conference on Information and Knowledge Management
Page Range / eLocation ID:
1079 to 1088
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The often fierce competition on crowdfunding markets can significantly affect project success. While various factors have been considered in predicting the success of crowdfunding projects, to the best knowledge of the authors, the phenomenon of competition has not been investigated. In this paper, we study the competition on crowdfunding markets through data analysis, and propose a probabilistic generative model, Dynamic Market Competition (DMC) model, to capture the competitiveness of projects in crowdfunding. Through an empirical evaluation using the pledging history of past crowdfunding projects, our approach has shown to capture the competitiveness of projects very well, and significantly outperforms several baseline approaches in predicting the daily collected funds of crowdfunding projects, reducing errors by 31.73% to 45.14%. In addition, our analyses on the correlations between project competitiveness, project design factors, and project success indicate that highly competitive projects, while being winners under various setting of project design factors, are particularly impressive with high pledging goals and high price rewards, comparing to medium and low competitive projects. Finally, the competitiveness of projects learned by DMC is shown to be very useful in applications of predicting final success and days taken to hit pledging goal, reaching 85% accuracy and error of less than 7 days, respectively, with limited information at early pledging stage. 
    more » « less
  2. null (Ed.)
    Abstract Insect epithelial cells contain cellular extensions such as bristles, hairs, and scales. These cellular extensions are homologous structures that differ in morphology and function. They contain actin bundles that dictate their cellular morphology. While the organization, function, and identity of the major actin-bundling proteins in bristles and hairs are known, this information on scales is unknown. In this study, we characterized the development of scales and the role of actin bundles in the mosquito, Aedes aegypti . We show that scales undergo drastic morphological changes during development, from a cylindrical to flat shape with longer membrane invagination. Scale actin-bundle distribution changes from the symmetrical organization of actin bundles located throughout the bristle membrane to an asymmetrical organization. By chemically inhibiting actin polymerization and by knocking out the forked gene in the mosquito ( Ae-Forked ; a known actin-bundling protein) by CRISPR-Cas9 gene editing, we showed that actin bundles are required for shaping bristle, hair, and scale morphology. We demonstrated that actin bundles and Ae-Forked are required for bristle elongation, but not for that of scales. In scales, actin bundles are required for width formation. In summary, our results reveal, for the first time, the developmental process of mosquito scale formation and also the role of actin bundles and actin-bundle proteins in scale morphogenesis. Moreover, our results reveal that although scale and bristle are thought to be homologous structures, actin bundles have a differential requirement in shaping mosquito scales compared to bristles. 
    more » « less
  3. Adding new unlicensed wireless spectrum is a promising approach to accommodate increasing traffic demand. However, unlicensed spectrum may have a high risk of becoming congested, and service providers (SPs) may have difficulty to differentiate their wireless services when offering them on the same unlicensed spectrum. When SPs offer identical services, the resulting competition can lead to zero profits. In this work, we consider the case where an SP bundles its wireless service with a content service. We show that this can differentiate the SPs’ services and lead to positive SP profits. In particular, we study the characteristics of the content services that an SP should bundle with its wireless service, and analyze the impact of bundling on consumer surplus. 
    more » « less
  4. We examine if the bundling of semiconducting carbon nanotubes (CNTs) can increase the transconductance and on-state current density of field effect transistors (FETs) made from arrays of aligned, polymer-wrapped CNTs. Arrays with packing density ranging from 20 to 50 bundles  μm −1 are created via tangential flow interfacial self-assembly, and the transconductance and saturated on-state current density of FETs with either (i) strong ionic gel gates or (ii) weak 15 nm SiO 2 back gates are measured vs the degree of bundling. Both transconductance and on-state current significantly increase as median bundle height increases from 2 to 4 nm, but only when the strongly coupled ionic gel gate is used. Such devices tested at −0.6 V drain voltage achieve transconductance as high as 50 μS per bundle and 2 mS  μm −1 and on-state current as high as 1.7 mA  μm −1 . At low drain voltages, the off-current also increases with bundling, but on/off ratios of ∼10 5 are still possible if the largest (95th percentile) bundles in an array are limited to ∼5 nm in size. Radio frequency devices with strong, wraparound dielectric gates may benefit from increased device performance by using moderately bundled as opposed to individualized CNTs in arrays. 
    more » « less
  5. Despite intense efforts in basic and clinical research, an individualized ventilation strategy for critically ill patients remains a major challenge. Recently, dynamic treatment regime (DTR) with reinforcement learning (RL) on electronic health records (EHR) has attracted interest from both the healthcare industry and machine learning research community. However, most learned DTR policies might be biased due to the existence of confounders. Although some treatment actions non-survivors received may be helpful, if confounders cause the mortality, the training of RL models guided by long-term outcomes (e.g., 90-day mortality) would punish those treatment actions causing the learned DTR policies to be suboptimal. In this study, we develop a new deconfounding actor-critic network (DAC) to learn optimal DTR policies for patients. To alleviate confounding issues, we incorporate a patient resampling module and a confounding balance module into our actor-critic framework. To avoid punishing the effective treatment actions non-survivors received, we design a short-term reward to capture patients' immediate health state changes. Combining short-term with long-term rewards could further improve the model performance. Moreover, we introduce a policy adaptation method to successfully transfer the learned model to new-source small-scale datasets. The experimental results on one semi-synthetic and two different real-world datasets show the proposed model outperforms the state-of-the-art models. The proposed model provides individualized treatment decisions for mechanical ventilation that could improve patient outcomes. 
    more » « less