ApproximateReality

An interactive simulation environment for the testing and optimization of algorithmic trading strategies.

An agent-based platform that is centered around a fully functioning limit order book and populations of agents that represent common market behaviors and strategies.


Benefits

Reduce bias and
focus on dynamics
of interest.
Reproduce all the
main empirical
regularities.
Model regulatory
and structural
changes.
Model against
unusual financial
market conditions.

Why Agent-Based Modeling?

Agent Based Models provide an in silico lab, where we can:

1. Capture our understanding of systems.

2. Test that understanding of the systems for coherence and comprehensiveness.

3. See how theory at the individual level creates aggregate patterns.

4. Validate that theory against real data at the aggregate and individual scale.

5. Make predictions about the system.

6. Test "what if?" scenarios to inform planning.

The caveat is that we need a good theory and causal hypotheses about how the system we are studying works. Simulation works best when the processes of the system under study are well-understood such that high-fidelity simulations are able to match predicted output.

How does it work?

1

For a model to be adequate, it has to be ‘true’ in the sense that it represents a plausible candidate for the true data-generating process of the phenomenon of interest. Think of there being a real-world data generating process and a model data-generating process. The latter must be simpler than the former, and its ‘goodness’ is to be evaluated by comparing simulated outputs and real-world observations.


Our ABM environment offers the ability to re-create the data generating process, producing synthetic market data that is indistinguishable from a given real-world time series. This has the significant advantage of parameter adjustment which enables users to construct any potential scenario they choose. By introducing multiple potential market dynamics, firms can ensure their algos function under many types of stressed scenarios and are performant in the broadest range of eventualities.

2

3

The individual ‘agents’ inside the simulation are themselves autonomous trading algorithms, and the micro-level interactions of these entities, as they take trading decisions and submit orders to a venue, are what produces the synthetic market data. An execution algo can be inserted into this agent-based framework while the simulation is running, not only showing how it reacts to other algorithms but also simulating the emergent behavior of the market in response to such trades.


Advantages

Agent-based simulators are calibrated and optimized against historical data to ensure that they produce data that is indistinguishable from the real world. Once the simulation faithfully creates market data, the underlying parameters are tweaked to produce novel data.
Explore extreme market events
The simulations are stochastic in nature and running them multiple times will generate a range of outcomes. By running the same simulation thousands of times, one can produce tail events, stressed conditions and market crashes. Special scenarios can also be run in order to produce large amounts of data.

Applications

Accurately model market impact
Uniquely, agent-based simulation allows you to run the same simulation thousands of times with or without an order. In comparing the results of the two it is possible to more accurately quantify the likely impact of a trade.
Offer greater transparency to regulators
Agent-based simulation allows you to demonstrate to regulators that you have tested your algos in a broad range of environments and prove that there is no way your algos can contribute to disorderly market conditions.

Let’s Talk!