Problem Statements
This TechSprint will be centred around three main problem statements to explore:
Problem Statement 1. Improved accuracy of market abuse detection:
How can AI in post trade market abuse surveillance help reduce false positives, produce a higher proportion of true positives, resulting in more accurate alerts and signals.
We would like to see solutions factoring in:
- Resilient approaches to market stress events and high volatility conditions that may lead to abnormal alerts: Incorporating the conditions of the market at a specific point in time, allowing for constant and automatic calibration to reduce false positives while retaining sensitivity in the identification of genuine abuse.
- Adaptiveness & future proofing, allowing for more dynamic surveillance parameters that will change to reflect evolving market conditions
- Tracking and monitoring emerging or evolving patterns of abuse
Problem Statement 2. Detection of instances of complex market abuse:
How can AI identify signals or instances of more complex types of market abuse, involving the analysis of multiple datasets, that traditional rules-based surveillance tools currently struggle to identify.
We would like to see solutions factoring in:
- Cross-product analysis: Identifying activity whereby entering orders to trade or executing trades in one product is undertaken with the intention of impacting the price of a related product. Using AI to identify correlations on a systematic and ongoing basis of different products and identify suspicious trading behaviour
- Cross-market analysis: Analysing data from multiple trading venues to detect market abuse activity, e.g., activity on one venue undertaken with the intent of artificially influencing or impacting a related product on another venue.
Problem Statement 3. Transforming market abuse surveillance by incorporating anomaly detection:
How can AI help identify market and trading anomalies indicative of market abuse, manipulative strategies, and disruptive trading practices that may give market participants an unfair advantage.
We would like to see solutions factoring in:
- Analysing historical market data, trading behaviours, news events, and other data sources to develop models or algorithms that can proactively flag potential instances of market abuse
When submitting your application, please make sure you are clear on the problem statement that you have chosen to address, with an overview of your proposed solution. While we do not expect you to have a comprehensive solution at the start, you should be able to provide an example of how you plan to tackle your chosen problem statement and the gap you are trying to address with your solution.
For all problem statements, solutions should take a user-centric approach, ensuring propositions or designs that are easy to use and understand for a diverse range of users. Similarly, the principles of inclusivity, transparency, and ethical use of data should be at the core of all the solutions.
Teams will be allocated to one problem statement to focus on throughout the TechSprint, however we do encourage participants to take a broader, flexible approach to solution development and to be as innovative as possible.
You can indicate a preference of problem statement in your registration form, which we will then take into consideration when reviewing and building out the teams.