Data input:

  • non structured data: news, social media, blogs etc.

Application:

  • market moving events: wheter a tweet will have a market impact

  • sentiment anlaysis

  • topic classification: document coming in, about which company, which subject

Challenges:

  • low latency: multi threading
  • high accuracy: software reliability, model precision
  • privacy
  • fairness

Opportunities:

  • Collaboration with academia: grants and research ties
⤧  Previous post Data Wrangling ⤧  Next post Git