DeepSuccess

The advances of Deep Learning in this decade, such as convolutional neural networks has been applied in many downstream classification and prediction tasks. In this project, we will develop a model for predicting the success of tech startups such as Initial Coin Offering (ICO) and kickstarter compaigns (e.g. crowdfunding). The observed data used for learning of a startup include its website, whitepaper, and codebase and can be extended to news and social media.

Potential resources: paper1, paper2

Deliverables: datasets, codebase, trained models, accuracy results, web or mobile app (OPTIONAL)

The project requires programming skills in Python, PyTorch (or Tensorflow, etc.). Competent knowledge and experience in Deep Learning. Pro-active in learning new things.