Asset Management

Asset managers face increased competition and elevated fee pressure, in an uncertain world of experimental monetary policy and macroeconomic volatility. Never has it been more critical to outperform benchmarks while taking a data-driven approach to risk. But current machine learning systems fail to separate signals from noise in complex time-series data. 

Causal AI understands, explains and predicts financial markets, offering the next generation of portfolio optimization and risk management capability, enabling asset managers to unlock latent market value.

 

Modern challenges in capital markets are well known

Investors demand lower fees and greater explainability from discretionary managers, while systematic funds must constantly extract new signals from an ocean of marginally useful data. Asset managers can turn to Machine Learning to stay on top of the problem, but current AI techniques are often inadequate:

  • Basic AutoML techniques are widely used, and their capacity to produce alpha has diminished
  • Non-causal ML techniques based on pairwise relationships will necessarily overfit to the past, leading to high risk and low understanding around future regime changes and unexpected events. 
  • They fail to translate predictions and models into actionable trading decisions.

Solutions

causalNet is a state-of-the-art modelling system that extracts the causal drivers from large datasets and marries them with human domain knowledge in one single streamlined process. The resulting constrained neural network outperforms non-causal AutoML models in out-of-sample testing on a huge range of forecasting tasks, ready to feed into any trading strategy.

Causal Discovery uncovers the driving forces behind cross-sectional returns, allowing for the robust construction of latent variables for factor analysis as well as the discovery of new factors beyond those found by standard correlation or PCA techniques.

Using causalNet, we can construct factor portfolios that systematically control for unintended exposures — removing cross-correlation effects between factors and dynamically constructing factors based on data, rather than imposing arbitrary definitions.

Our Causal Discovery methods can identify the true causal drivers of exposure for a portfolio, rather than focusing on spurious correlations. Using causalNet, we can generate realistic scenarios that capture fundamental regime shifts during periods of market stress while also remaining intuitive and explicable.  

In today’s market, having the right data is a key to success. Evaluating the quality of data is nonetheless a challenging task. With causaLens this task is made easier with our proprietary dataset evaluator: benchmark the candidate data against public datasets and quantify the impact of the data on your KPIs, while avoiding the spurious correlations in all large datasets.

Portfolio construction methods based on correlation matrices impose penalties on spurious factors, limiting performance. causaLens has pioneered Causal Hierarchical Risk Parity, a portfolio optimization model based on robust causal clustering techniques that produces lower volatility and higher risk-adjusted returns than the traditional techniques. Read more about how it is being used here.

Poor input signals will lead to poor results in any forecasting task. The causaLens platform feature engineering pipeline generates a fully customizable set of features while automatically controlling for redundancy and statistical significance, greatly enhancing the search space while avoiding the problems of exponential runaway.

Why causaLens

Which level is your organisation in?

0

No Machine Learning

  • Do you think it would take you years to become an AI-driven Enterprise?
  • Is the value of your enterprise’s data asset largely unrealised?
  • Are the predictions, insights and business decisions compromised due to human error?
  • Are resources wasted improvising solutions to problems that could be better solved with ML?
1

Manual Machine Learning

  • Is it hard to build and retain Quant teams?
  • Does it take months or years to achieve real business impact?
  • Is the team mostly reactive, responding to requests from business functions for analytics?
  • Does your team spend their time implementing repetitive & expensive processes?
2

Automated Machine Learning

  • Do you find that generic Data Science Platforms overfit & underperform in asset management?
  • Do you have trouble translating predictive models & predictions to real value for the business?
  • Are generic platforms not flexible or transparent enough while failing to incorporate your domain expertise?

Systematic Trading

Causal AI examines entire dynamic systems to understand the true causal relationships that drive change – relationships that cannot be found with correlation-based techniques. These new angles can be employed in signals research, execution and risk management to create investment opportunities that persist and are robust to unexpected regime changes.

causaLens combines up-to-date academic methods with proprietary R&D from a leading causality research lab. The platform fits easily into existing pipelines, allowing systematic investors to move ahead of existing approaches by applying causal techniques across the business.

Discretionary Asset-Management

Causal AI allows domain experts to include their own assumptions into the model, producing a new class of intelligence that learns from data, but within a contextualized view of the world. Discretionary managers can have the best of both worlds, where their expertise is augmented by state-of-the-art artificial intelligence, without relying on a black-box to get insights from data. These insights empower users to harness the full potential of their domain knowledge and become ‘quantamental’ managers.

See causaLens’ Economic Analysis and Risk Management solutions, designed for discretionary managers to use via our intuitive asset management toolkit. 

High Frequency Trading & Market Making

causaLens can be integrated directly into any pipeline to optimise high-frequency trading strategies, trade execution, and market making. Designed for high-throughput online time series prediction, our models continuously adapt in real time to discover the current causal drivers in the market and produce the most efficient execution.

Private Equity & Real Estate

Private equity investors often work in low-data regimes in which standard machine learning techniques are prone to overfit, because they confuse correlation with causation. But data-driven approaches can produce outperformance when used properly. causaLens produces robust, explainable insights and actionable forecasts from limited data, and our causalNet technology allows domain experts to embed their knowledge directly into the AI.

Data Search & Building New Products

causaLens empowers exchanges, data sourcing teams & data vendors to autonomously discover value in time-series data. Standard AI techniques are confused by large amounts of intercorrelated and mismatched data; only Causal AI allows users to extract valuable signals and build exciting data products that are easily monetized.

Leading asset managers use our portfolio optimization solution

Our CEO, Dr. Darko Matovski, presents a Portfolio Optimization Demo during the ‘Beyond Spurious Correlations: Understanding Portfolio Risk with Causal AI’ webinar.

Watch the full webinar
Play video

Learn how CLS Group is using causaLens to autonomously find value in their data.

Find out about the drivers of currency returns in periods of market stress

Start optimizing your business today

Request a demo