Related Experiment Videos
Computational learning techniques for intraday FX trading using popular technical indicators.
M H Dempster1, T W Payne, Y Romahi
1Centre for Financial Research, Judge institute of Management, University of Cambridge, Cambridge, UK.
IEEE Transactions on Neural Networks
|February 6, 2008
Summary
Computational learning strategies for profitable trading rules show promise. Genetic algorithms outperform other methods, especially with transaction costs, but realistic costs limit profitability and overfitting is a risk.
Area of Science:
- Computational finance
- Machine learning in finance
- Algorithmic trading
Background:
- Technical indicators are widely used in financial markets.
- Developing profitable trading rules from these indicators is a complex challenge.
- Computational learning offers potential solutions for automated trading strategy development.
Purpose of the Study:
- To compare the effectiveness of different computational learning approaches for generating profitable trading rules.
- To evaluate the performance of reinforcement learning and genetic programming against simpler methods.
- To analyze the impact of transaction costs and overfitting on trading strategy profitability.
Main Methods:
- Utilized reinforcement learning and genetic programming as primary computational learning methods.
- Compared these with a Markov decision problem exact solution and a heuristic approach.
- Employed a collection of popular technical indicators as input features for trading rules.
Main Results:
- All methods generated significant profits with zero transaction costs.
- Genetic algorithms demonstrated superiority in the presence of non-zero transaction costs.
- No method yielded significant profits at realistic transaction cost levels.
- A substantial risk of overfitting was identified when in-sample learning was unconstrained.
Conclusions:
- Genetic programming is a promising approach for developing trading rules from technical indicators, particularly when accounting for transaction costs.
- Realistic transaction costs significantly diminish the profitability of automated trading strategies.
- Careful constraint of in-sample learning is crucial to mitigate overfitting and ensure robust out-of-sample performance.
Related Concept Videos
01:25First Derivative Test: Problem Solving
Imagine an asset price that crashes to a low point, rebounds sharply as bargain-hunters step in, and then gradually declines. Such behavior can be modeled with a smooth function whose turning points represent locally overvalued and undervalued regions. A convenient example that captures rebound followed by decay is:The high and low points of this curve are identified using the first derivative test, which determines where the function changes from increasing to decreasing or vice versa. To...
01:20Deconvolution
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
01:29Econometric Views (EViews)
Econometric Views, often stylized as EViews, is a package that merges statistical analysis with econometric studies. It is designed to provide tools for time series analysis, forecasting, and econometric model simulation. The software originated from MicroTSP software and has evolved significantly since its inception in 1981. The history of EViews is marked by a continuous effort to enhance its computational speed and user interface. It was initially developed for large computing systems but...
01:30Derivatives of Inverse Trigonometric Functions
A ship tracking an approaching aircraft relies on geometric measurements to find out the aircraft’s position relative to the observer. By measuring the slant distance to the aircraft and the angle of elevation, the horizontal and vertical components of the distance can be obtained using trigonometric relationships. This geometric approach provides a basis for analyzing how the observed angle changes as the aircraft moves closer to the ship.To examine the mathematical behavior of the angle of...
01:24Convolution: Math, Graphics, and Discrete Signals
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
01:10Reconstruction of Signal using Interpolation
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...