AIDA Finance
The AIDA-Finance Lab, formerly known as the Financial Signal Processing (FSP) Laboratory, was created in 2014 with a vision of bringing professionals from academia and industry together to promote research in quantitative finance using engineering tools, with a special focus on artificial intelligence, signal processing and optimisation techniques.
We have been working with leading financial organisations in various areas and subjects in order to address complex issues in quantitative finance. We collaborate with Investment Banks, Hedge Funds, and Asset Management firms to find better solutions for their problems.
Our academic team consists of people with wide-range of expertise from signal processing to hardware acceleration for fast computing. We strongly believe that engineering techniques and mindset are heavily under-used in solving financial problems.
All our academic visitors have both advanced engineering degrees and extensive experience in finance, including Managing directors from top tier banks and CEOs of quantitative hedge funds. By holding regular sessions with our academic visitors, who have already applied engineering approach towards problems in finance, we have a unique advantage to ensure that our research has significant practical impact and is directly applicable to current problems in quantitative finance.
Topics
-
Generative AI for Financial Decision-making
Fostering the development of generative AI techniques in algorithmic trading, risk management, portfolio optimization, and fraud detection. Together with augmented and surrogate datasets enhanced deep modelling strategies.
-
Financial Signal Processing & Modelling
Developing advance signal processing techniques to extract valuable insights from financial data and build robust financial models for efficient decision-making.
-
Optimization & Systems Theory for Finance
Optimising financial systems using advanced mathematical frameworks and control theory, ensuring optimal resource allocation and system stability.
-
Natural Language Processing (NLP) for Financial Text Analysis
Exploring applications of Large Language Models (LLMs) for extracting nuanced insights from unstructured data to inform trading strategies and market predictions.
-
Graph Theory for Fintech-AI
Applying graph theory to model complex financial networks, exploiting the locality of information to enhance portfolio management.
-
Big Data Analytics in Financial Markets
Analysing high-frequency trading data to uncover trading patterns and enhance algorithmic trading strategies, and employing AI to interpret large-scale finance data.
Selected Publications from AIDA-Finance
-
![]()
FinLlama: LLM-Based Financial Sentiment Analysis for Algorithmic Trading
-
![]()
Analysis of Global Fixed-Income Returns Using Tensor Algebra
-
![]()
Portfolio Cuts: A Graph-Theoretic Framework to Diversification
Other Publications from AIDA-Finance
Graph and tensor-train recurrent neural networks for high-dimensional models of limit order books
Financial News Classification Model for NLP-based Bond Portfolio Construction
Two analog neural models with the controllability on number of assets for sparse portfolio design
Analysis of Global Fixed-Income Returns Using Multilinear Tensor Algebra
MAFI: A Multi-Asset Fragility Indicator Using Principal Component Analysis
Computational Results for a Quantum Computing Application in Real-Life Finance
Estimation of Financial Indices Volatility Using a Model with Time-Varying Parameters
Hierarchical Graph Learning for Stock Market Prediction Via a Domain-Aware Graph Pooling Operator
Graph-regularized tensor regression: A domain-aware framework for interpretable multi-way financial modelling