Related Experiment Video
Updated: Jun 10, 2025
08:27
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
993
DeepVol: volatility forecasting from high-frequency data with dilated causal convolutions
Fernando Moreno-Pino1,2, Stefan Zohren1,3
1Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, UK.
Quantitative Finance
|October 16, 2024
Summary
DeepVol, a novel deep learning model, forecasts equity volatility using high-frequency financial data. This approach enhances prediction accuracy by effectively utilizing intraday information, outperforming traditional methods for better risk management.
Area of Science:
- Quantitative Finance
- Machine Learning
- Financial Econometrics
Background:
- Volatility forecasting is crucial for equity risk assessment.
- Traditional statistical models and machine learning techniques are used for daily time-series volatility prediction.
- High-frequency intraday data can improve volatility predictions.
Purpose of the Study:
- To propose DeepVol, a novel model using Dilated Causal Convolutions for day-ahead volatility forecasting.
- To leverage high-frequency intraday data for enhanced volatility prediction accuracy.
- To demonstrate the effectiveness of deep learning in capturing predictive information from financial time-series.
Main Methods:
- Utilized Dilated Causal Convolutions for time-series analysis.
- Employed high-frequency intraday financial data from NASDAQ-100 over two years.
- Evaluated DeepVol's performance against traditional methodologies.
Main Results:
- Dilated convolutional filters effectively extract relevant information from intraday financial time-series.
- DeepVol successfully leverages predictive information present in high-frequency data.
- The model avoids limitations of daily data models, such as model misspecification and handcrafted features.
Conclusions:
- DeepVol, a deep learning-based approach, accurately learns global features from high-frequency data.
- The proposed model yields more accurate volatility predictions compared to traditional methods.
- DeepVol contributes to producing more reliable equity risk measures.
Keywords:
Deep learningDilated causal convolutionsHigh-frequency dataRealised volatilityVolatility forecastingMore Related Videos
Related Concept Videos
01:24Convolution: Math, Graphics, and Discrete Signals
234
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...
234
01:03Prediction Intervals
2.2K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.2K
01:17Convolution Properties II
174
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
174
01:20Convolution Properties I
140
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
140
01:20Deconvolution
137
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...
137
01:26Linear Approximation in Frequency Domain
87
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
87