Implementing a Backtesting System

A backtest is a simulation of a model-driven investment strategy's response to historical data. While working on designing and developing a backtest, it would be helpful to think in terms of the concept of creating video games.

In this chapter, we will design and implement an event-driven backtesting system using an object-oriented approach. The resulting profits and losses of our trading model may be plotted on to a graph to help visualize the performance of our trading strategy. However, is this sufficient enough to determine whether it is a good model?

There are many concerns to be addressed in backtesting—for example, the effects of transaction costs, execution latency of orders, access to detailed transactions, and quality of historical data. Notwithstanding these factors, the primary goal of creating a backtesting system is to...

Introducing backtesting

A backtest is a simulation of a model-driven investment strategy's response to historical data. The purpose of performing experiments with backtests is to make discoveries about a process or system. By using historical data, you can save time in testing an investment strategy for the period forward. It helps you test an investment theory based on the movements of the tested period. It is also used to both evaluate and calibrate an investment model. Creating a model is only the first step. The investment strategy will typically employ the model to help you drive simulated trading decisions and compute various factors related to either risk or return. These factors are typically used together to find a combination that is predictive of return.

Concerns in...

Designing and implementing a backtesting system

Now that we have an idea of designing a video game for creating a backtesting trading system, we can begin our object-oriented approach by first defining the required classes for the various components in our trading system.

We are interested in implementing a simple backtesting system to test a mean-reverting strategy. Using the daily historical prices from a data-source provider, we will take the closing price of each day to compute the volatility of price returns for a particular instrument, using the AAPL stock price as an example. We would like to test a theory that if the standard deviation of returns for an elapsed number of days is far from the mean of zero by a particular threshold, a buy or sell signal is generated. When such a signal is indeed generated, a market order is sent to the exchange to be executed at the opening...

Ten considerations for a backtesting model

In the previous section, we performed one replication of a backtest. Our result looks pretty optimistic. However, is this sufficient to deduce that this is a good model? The truth is that backtesting involves a lot of research that merits literature of its own. The following list briefly covers some thoughts that you might want to consider when implementing your backtests.

Resources restricting your model

The resources that are available to your backtesting system limit how well you can implement your backtest. A financial model that generates signals using only the last closing price needs a set of historical data on the closing prices. A trading system that requires reading from...

Discussion of algorithms in backtesting

After taking into consideration the designing of a backtesting model, one or more algorithms may be used to improve the model on a continuous basis. This section briefly covers some of the algorithmic techniques used in areas of backtesting, such as data mining and machine learning.

K-means clustering

The k-means clustering algorithm is a method of clustering analysis in data mining. From the backtest results of n observations, the k-means algorithm is designed to classify the data into k clusters based on their relative distance from one another. The center point of each cluster is computed. The objective then is to find the within-cluster sum of squares that gives us a model-averaged...

Summary

A backtest is a simulation of a model-driven investment strategy's response to historical data. The purpose of performing experiments with backtests is to make discoveries about a process or system and to compute various factors related to either risk or return. The factors are typically used together to find a combination that is predictive of the return.

While working on designing and developing a backtest, it would be helpful to think in terms of the concept of creating video games. In a virtual trading environment, components are needed for the simulation of price feeds, the order-matching engine, the order book management, as well as functions for account and position updates. To achieve these functionalities, we can explore the concept of an event-driven backtesting system.

In this chapter, we designed and implemented a backtesting system that interacts with...