Pricing a firm’s Initial Public Offering (IPO) has historically been very difficult, with high average returns on the first-day of trading. Furthermore, IPO withdrawal, the event in which companies who file to go public ultimately rescind the application before the offering, is an equally challenging prediction problem. This research utilizes word embedding techniques to evaluate existing theories concerning firm sentiment on first-day trading performance and the probability of withdrawal, which has not yet been explored empirically. The results suggest that firms attempting to go public experience a decreased probability of withdrawal with the increased presence of positive, litigious, and uncertain language in their initial prospectus, while the increased presence of strong modular language leads to an increased probability of withdrawal. The results also suggest that frequent or large adjustments in the strong modular language of subsequent filings leads to smaller first-day returns.

Human health coaching has been established as an effective intervention for improving clients’ health, but it is restricted in scale due to the availability of coaches and finances of the clients. We aim to build a scalable, automated system for physical activity coaching that is similarly grounded in behavior change theories. In this paper, we present our initial steps toward building a flexible system that is capable of carrying out a natural dialogue for goal setting as a health coach would while also offering additional support through just-in-time adaptive interventions. We outline our modular system design and approach to gathering and analyzing data to incrementally implement such a system.