Delivering Algo Performance through Enhanced Market Simulation
The global shift toward unbundling of research services from execution is forcing sell-side institutions to focus on differentiating their service offerings as they vie for buy-side liquidity in an increasingly competitive marketplace. With soft-commissioned research and high-speed connectivity to trading venues no longer potent as differentiators, the sell side is acknowledging that the quality and performance of trading strategies and algorithmic models is key to attracting and retaining client order flow.
Achieving competitive performance levels requires rigorous testing and performance evaluation on realistic market data. Yet firms face a raft of obstacles and technical challenges that can restrict their ability to qualify for inclusion in the ‘algo wheels’ operated by their clients: the lists of preferred (and approved) broker trading strategies they are able to use.
This whitepaper – based on a survey of 15 sell-side executives involved in algo trading – evaluates current challenges around trade execution and algo testing in simulated market environments and explores their current operating procedures.
It also discusses how a new approach to developing a highly granular, dynamic representation of the markets using agent-based simulation (ABS) techniques could help reduce bias and focus on dynamics of interest, such as stylized facts, allowing firms to optimise execution system performance as well as the ability of their algorithms to attract and retain buy-side liquidity.