Financial Informatics Research in Glasgow

Success in Financial Markets is driven by complex interactions between core business fundamentals, investor perception and world events. Traders, financial analysists, regulators and governments need to collate and analyse this information to effectively perform their roles. However. In our modern globalized economy, it is no longer possible for one person to fully understand all of these factors and interactions, due to the increased complexity, the number of stakeholders involved, as well as increasing attempts to obscure or misconstrue information. At the School of Computing Science we believe that the future of financial markets lies in the development of sophisticated AI assistive agents, which can collate, analyse and apply financial data in real-time and at scale for customers, where our core research is focused on how to effectively create, train, evaluate and explain such agents.

Interested in Collaborations? Contact Dr. Richard McCreadie

Research Topics


  • Know Your Asset
    • Automatic Collation of Asset Profiles from Web Search Results
  • Fact Extraction from Online Documents
    • Analysing Financial Reports to extract company performance
    • Analysing Financial News articles to identify key Financial Events
  • Financial Knowledge Graphs
    • Construction of Financial Knowledge Graphs from existing repositories
    • Construction of Financial Knowledge Graphs from online reports
  • Collecting Financial Discussions on Social Media
    • Automatic discovery and crawling of emerging financial topics on social media


  • Technical Analysis
    • Production of technical indicators in real-time and at scale
  • Understanding Public Perceptions regarding Financial Entities
    • Using Social Media to track Asset perception across user groups
    • Analysing Social Media to identify coordinated attempts to manipulate public perception regarding assets
  • Financial Knowledge Graph Embedding
    • Converting human interpretable knowledge graphs to AI-usable vectors
    • Temporal Embeddings


  • Forecasting Financial Asset Performance
    • Forecasting performance using technical analysis
    • Forecasting performance using investment patterns
    • Enhancing Forecasting across Cross-Markets
  • Trading Strategies
    • Portfolio Construction
    • Trading Strategy Simulation
    • Learning-to-Trade
    • What-if analysis
  • Financial Asset Recommendation
    • Recommendations from Price/Trend/Profitability predictions
    • Recommendations from Customer Investment History
  • Automatic Asset Profile Construction
    • Generative summarization of asset descriptions and key events



Prof. Iadh Ounis Banner

Prof. Craig Macdonald Banner

Dr. Richard McCreadie Banner

Dr. Javier Sanz-Cruzado Banner

Open Source Technologies

Real-time Financial Technical Indicator Generation in Apache Flink

Building, Evaluating and Tuning Automated Recommender Systems

REcommending LInks in SOcial Networks

Terrier IR Platform