← Back to portfolio

SK C&C · Jul 2019 – Mar 2020

Market Caster: News-based Market Prediction

Role · Event-prediction and sentiment models

01Background & Goals

  • An AI and big-data platform that forecasts market indicators such as global indices and bonds over several horizons.
  • Structured data was analyzed as time series, while financial events were extracted from unstructured news for prediction.

02Contributions

Event extraction and embedding
  1. Extracted the core components (actor, action, object) of news sentences
  2. Embedded event tuples with a neural tensor network and analyzed sentence similarity
Prediction models
  1. Predicted market events with a hierarchical event- and time-level attention model
  2. Built news sentiment modules (BERT, Naive Bayes) and ensembled structured- and unstructured-data models to predict market moves

03Tech Stack

Framework / Platform
PyTorch, scikit-learn
Methodology
Hierarchical attention, Neural tensor network, Sentiment analysis

04Reference Material