Placeholder image for staff profiles

Yi Cao


Lecturer in Business Analytics

Biography

My qualifications

CFA
Chartered Financial Analyst

Previous roles

01 January 2016 - 01 September 2017
Lecturer in Computational Finance
CCFEA, University of Essex
01 November 2014 - 31 December 2015
Quantitative Analyst
Susquehanna International Group, LLP: SIG

Affiliations and memberships

EFA
European Finance Association
BAFA
The British Accounting and Finance Association (BAFA)

Research

Research interests

Research collaborations

My teaching

My publications

Publications

Luo Y, Fu Q, Liu J, Harkin J, McDaid L, Cao Y (2017) An Extended Algorithm Using Adaptation of Momentum and Learning Rate for Spiking Neurons Emitting Multiple Spikes, Lecture Notes in Artificial Intelligence 10305 pp. 569-579 Springer Verlag
This paper presents two methods of using the dynamic momentum and learning rate adaption, to improve learning performance in spiking neural networks where neurons are modelled as spiking multiple times. The optimum value for the momentum factor is obtained from the mean square error with respect to the gradient of synaptic weights in the proposed algorithm. The delta-bar-delta rule is employed as the learning rate adaptation method. The XOR and Wisconsin breast cancer (WBC) classification tasks are used to validate the proposed algorithms. Results demonstrate no error and a minimal error of 0.08 are achieved for the XOR and WBC classification tasks respectively, which are better than the original Booij?s algorithm. The minimum number of epochs for XOR and Wisconsin breast cancer tasks are 35 and 26 respectively, which are also faster than the original Booij?s algorithm ? i.e. 135 (for XOR) and 97 (for WBC). Compared with the original algorithm with static momentum and learning rate, the proposed dynamic algorithms can control the convergence rate and learning performance more effectively.
Cao Y, Li Y, Coleman S, Belatreche A, McGinnity T (2014) Detecting wash trade in the financial market, 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) pp. 85-91
Wash trade refers to the activities of traders who
utilise deliberately designed collusive transactions to increase the
trading volumes for creating active market impression. Wash
trade can be damaging to the proper functioning and integrity of
capital markets. Existing work focuses on collusive clique
detections based on certain assumptions of trading behaviours.
Effective approaches for analysing and detecting wash trade in a
real-life market have yet to be developed. This paper proposes a
new analysis approach for abstracting the basic structures of
wash trade based on the network topology theory and a novel
approach for detecting wash trade activities. The evaluation
experiments conducted on four NASDAQ stocks suggest that
wash trade actions can be effectively identified based on the
proposed algorithm.
Zhai J, Cao Y, Yao Y, Ding X, Li Y (2016) Coarse and fine identification of collusive clique in financial market, Expert Systems with Applications 69 pp. 225-238 Elsevier
Collusive transactions refer to the activity whereby traders use carefully-designed trade to illegally ma- nipulate the market. They do this by increasing specific trading volumes, thus creating a false impression that a market is more active than it actually is. The traders involved in the collusive transactions are termed as collusive clique. The collusive clique and its activities can cause substantial damage to the market?s integrity and attract much attention of the regulators around the world in recent years. Much of the current research focused on the detection based on a number of assumptions of how a normal market behaves. There is, clearly, a lack of effective decision-support tools with which to identify poten- tial collusive clique in a real-life setting. The study in this paper examined the structures of the traders in all transactions, and proposed two approaches to detect potential collusive clique with their activi- ties. The first approach targeted on the overall collusive trend of the traders. This is particularly useful when regulators seek a general overview of how traders gather together for their transactions. The sec- ond approach accurately detected the parcel-passing style collusive transactions on the market through analysing the relations of the traders and transacted volumes. The proposed two approaches, on one hand, provided a complete cover for collusive transaction identifications, which can fulfil the different types of requirements of the regulation, i.e. MiFID II, on the other hand, showed a novel application of well-known computational algorithms on solving real and complex financial problem. The proposed two approaches are evaluated using real financial data drawn from the NYSE and CME group. Experimental results suggested that those approaches successfully identified all primary collusive clique scenarios in all selected datasets and thus showed the effectiveness and stableness of the novel application.
Cao Y, Li Y, Coleman S, Belatreche A, McGinnity T (2015) Detecting Wash Trade in Financial Market Using Digraphs and Dynamic Programming, IEEE Transactions on Neural Networks and Learning Systems 27 (11) pp. 2351-2363 Institute of Electrical and Electronics Engineers (IEEE)
A wash trade refers to the illegal activities of
traders who utilize carefully designed limit orders to manually
increase the trading volumes for creating a false impression of
an active market. As one of the primary formats of market
abuse, a wash trade can be extremely damaging to the proper
functioning and integrity of capital markets. The existing
work focuses on collusive clique detections based on certain
assumptions of trading behaviors. Effective approaches for
analyzing and detecting wash trade in a real-life market have
yet to be developed. This paper analyzes and conceptualizes the
basic structures of the trading collusion in a wash trade by using
a directed graph of traders. A novel method is then proposed to
detect the potential wash trade activities involved in a financial
instrument by first recognizing the suspiciously matched orders
and then further identifying the collusions among the traders
who submit such orders. Both steps are formulated as a
simplified form of the knapsack problem, which can be solved
by dynamic programming approaches. The proposed approach
is evaluated on seven stock data sets from the NASDAQ and the
London Stock Exchange. The experimental results show that
the proposed approach can effectively detect all primary wash
trade scenarios across the selected data sets.
Cao Y, Li Y, Coleman S, Belatreche A, McGinnity T (2014) A Hidden Markov Model with Abnormal States for Detecting Stock Price Manipulation, 2013 IEEE International Conference on Systems, Man, and Cybernetics pp. 3014-3019 IEEE
Price manipulation refers to the act of using illegal trading behaviour to manually change an equity price with the aim of making profits. With increasing volumes of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. Effective approaches for analysing and real-time detection of price manipulation are yet to be developed. This paper proposes a novel approach, called Hidden Markov Model with Abnormal States (HMMAS), which models and detects price manipulation activities. Together with the wavelet decomposition for features extraction and Gaussian Mixture Model for Probability Density Function (PDF) construction, the HMMAS model detects price manipulation and identifies the type of the detected manipulation. Evaluation experiments of the model were conducted on six stock tick data from NASDAQ and London Stock Exchange (LSE). The results showed that the proposed HMMAS model can effectively detect price manipulation patterns.
Yao Y, Zhai J, Cao Y, Ding X, Liu J, Luo Y (2017) Data analytics enhanced component volatility model, Expert Systems with Applications 84 pp. 232-241 Elsevier
Volatility modelling and forecasting have attracted many attentions in both finance and computation ar- eas. Recent advances in machine learning allow us to construct complex models on volatility forecast- ing. However, the machine learning algorithms have been used merely as additional tools to the existing econometrics models. The hybrid models that specifically capture the characteristics of the volatility data have not been developed yet. We propose a new hybrid model, which is constructed by a low-pass fil- ter, the autoregressive neural network and an autoregressive model. The volatility data is decomposed by the low-pass filter into long and short term components, which are then modelled by the autoregressive neural network and an autoregressive model respectively. The total forecasting result is aggregated by the outputs of two models. The experimental evaluations using one-hour and one-day realized volatil- ity across four major foreign exchanges showed that the proposed model significantly outperforms the component GARCH, EGARCH and neural network only models in all forecasting horizons.
Cao Y, Li Y, Coleman S, Belatreche A, McGinnity T (2015) Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection, IEEE Transactions on Neural Networks and Learning Systems 26 (2) pp. 318-330 Institute of Electrical and Electronics Engineers (IEEE)
Price manipulation refers to the activities of those
traders who use carefully designed trading behaviors to manually
push up or down the underlying equity prices for making profits.
With increasing volumes and frequency of trading, price manipulation
can be extremely damaging to the proper functioning
and integrity of capital markets. The existing literature focuses
on either empirical studies of market abuse cases or analysis
of particular manipulation types based on certain assumptions.
Effective approaches for analyzing and detecting price manipulation
in real time are yet to be developed. This paper proposes
a novel approach, called adaptive hidden Markov model with
anomaly states (AHMMAS) for modeling and detecting price
manipulation activities. Together with wavelet transformations
and gradients as the feature extraction methods, the AHMMAS
model caters to price manipulation detection and basic manipulation
type recognition. The evaluation experiments conducted
on seven stock tick data from NASDAQ and the London Stock
Exchange and 10 simulated stock prices by stochastic differential
equation show that the proposed AHMMAS model can effectively
detect price manipulation patterns and outperforms the selected
benchmark models.
Zhai J, Cao Y, Yao Y, Ding X, Li Y (2016) Computational intelligent hybrid model for detecting disruptive trading activity, Decision Support Systems 93 pp. 26-41 Elsevier
The term ?disruptive trading behaviour? was first proposed by the U.S. Commodity Futures Trading Commission and is now widely used by US and EU regulation (MiFID II) to describe activities that create a misleading appearance of market liquidity or depth or an artificial price movement upward or downward according to their own purposes. Such activities, identified as a new form of financial fraud in EU regulations, damage the proper functioning and integrity of capital markets and are hence extremely harmful. While existing studies have explored this issue, they have, in most cases, either focused on empirical analysis of such cases or proposed detection models based on certain assumptions of the market. Effective methods that can analyse and detect such disruptive activities based on direct studies of trading behaviours have not been studied to date. There exists, accordingly, a knowledge gap in the literature. This paper seeks to address that gap and provides a hybrid model composed of two data-mining-based detection modules that effectively identify disruptive trading behaviours. The hybrid model is designed to work in an on-line scheme. The limit order stream is transformed, calculated and extracted as a feature stream. One detection module, ?Single Order Detection,? detects disruptive behaviours by identifying abnormal patterns of every single trading order. Another module, ?Order Sequence Detection,? approaches the problem by examining the contextual relationships of a sequence of trading orders using an extended hidden Markov model, which identifies whether sequential changes from the extracted features are manipulative activities (or not). Both models were evaluated using huge volumes of real tick data from the NASDAQ, which demonstrated that both are able to identify a range of disruptive trading behaviours and, furthermore, that they outperform the selected traditional benchmark models. Thus, this hybrid model is shown to make a substantial contribution to the literature on financial market surveillance and to offer a practical and effective approach for the identification of disruptive trading behaviour.
Zhai J, Cao Y (2014) On the calibration of stochastic volatility models: A comparison study, 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) pp. 303-309 IEEE
We studied the application of gradient based optimization methods for calibrating stochastic volatility models. In this study, the algorithmic differentiation is proposed as a novel approach for Greeks computation. The ?payoff function independent? feature of algorithmic differentiation offers a unique solution cross distinct models. To this end, we derived, analysed and compared Monte Carlo estimators for computing the gradient of a certain payoff function using four different methods: algorithmic differentiation, Pathwise delta, likelihood ratio and finite differencing. We assessed the accuracy and efficiency of the four methods and their impacts into the optimisation algorithm. Numerical results are presented and discussed.
Cao Y, Li Y, Coleman S, Belatreche A, McGinnity T (2014) Detecting price manipulation in the financial market, 2014 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) pp. 77-84
Market abuse has attracted much attention from financial regulators around the world but it is difficult to fully prevent. One of the reasons is the lack of thoroughly studies of the market abuse strategies and the corresponding effective market abuse approaches. In this paper, the strategies of reported price manipulation cases are analysed as well as the related empirical studies. A transformation is then defined to convert the time-varying financial trading data into pseudo-stationary time series, where machine learning algorithms can be easily applied to the detection of the price manipulation. The evaluation experiments conducted on four stocks from NASDAQ show a promising improved performance for effectively detecting such manipulation cases.
Zhai J, Cao Y, Ding X (2017) Data analytic approach for manipulation detection in stock market, Review of Quantitative Finance and Accounting 50 (3) pp. 897-932 Springer Verlag
The term ??price manipulation?? is used to describe the actions of ??rogue?? traders
who employ carefully designed trading tactics to incur equity prices up or down to make
profit. Such activities damage the proper functioning, integrity, and stability of the
financial markets. In response to that, the regulators proposed new regulatory guidance to
prohibit such activities on the financial markets. However, due to the lack of existing
research and the implementation complexity, the application of those regulatory guidance,
i.e. MiFID II in EU, is postponed to 2018. The existing studies exploring this issue either
focus on empirical analysis of such cases, or propose detection models based on certain
assumptions. The effective methods, based on analysing trading behaviour data, are not yet
studied. This paper seeks to address that gap, and provides two data analytics based
models. The first one, static model, detects manipulative behaviours through identifying
abnormal patterns of trading activities. The activities are represented by transformed limit
orders, in which the transformation method is proposed for partially reducing the nonstationarity
nature of the financial data. The second one is hidden Markov model based
dynamic model, which identifies the sequential and contextual changes in trading behaviours.
Both models are evaluated using real stock tick data, which demonstrate their
effectiveness on identifying a range of price manipulation scenarios, and outperforming the
selected benchmarks. Thus, both models are shown to make a substantial contribution to
the literature, and to offer a practical and effective approach to the identification of market
manipulation.
Zhang J, Liu J, Luo Y, Fu Q, Bi J, Qiu S, Cao Y, Ding X (2017) Chemical Substance Classification using Long Short-Term Memory Recurrent
Neural Network,
IEEE Conference Proceedings ICCT 2017 IEEE
This paper proposed a chemical substance detection
method using the Long Short-Term Memory of Recurrent
Neural Networks (LSTM-RNN). The chemical substance data
was collected using a mass spectrometer which is a time-series
data. The classification accuracy using the LSTM-RNN
classifier is 96.84%, which is higher than 75.07% of the ordinary
feed forward neural networks. The experimental results show
that the LSTM-RNN can learn the properties of the chemical
substance dataset and achieve a high detection accuracy.
Fu Q, Luo F, Liu J, Bi J, Qui S, Cao Y, Ding X (2018) Improving Learning Algorithm Performance for Spiking Neural Networks, IEEE Conference Proceedings ICCT 2017 IEEE
This paper proposes three methods to improve the
learning algorithm for spiking neural networks (SNNs). The aim
is to improve learning performance in SNNs where neurons are
allowed to fire multiple times. The performance is analyzed
based on the convergence rate, the concussion condition in the
training period and the error between actual output and desired
output. The exclusive-or (XOR) and Wisconsin breast cancer
(WBC) classification tasks are employed to validate the
proposed optimized methods. Experimental results demonstrate
that compared to original learning algorithm, all three methods
have less iterations, higher accuracy, and more stable in the
training period.
Luo Y, Wan L, Liu J, Cao Y (2017) An Efficient Hardware Architecture for Multilayer Spiking Neural Networks, Neural Information Processing 24th International Conference, ICONIP 2017 Guangzhou, China, November 14?18, 2017 Proceedings, Part III Springer International Publishing
Spiking Neural Network (SNN) is the most recent computa
tional model that can emulate the behaviors of biological neuron system.
This paper highlights and discusses an efficient hardware architecture for
the hardware SNNs, which includes a layer-level tile architecture (LTA)
for the neurons and synapses, and a novel routing architecture (NRA)
for the interconnections between the neuron nodes. In addition, a visu
alization performance monitoring platform is designed, which is used as
functional verification and performance monitoring for the SNN hard
ware system. Experimental results demonstrate that the proposed archi
tecture is feasible and capable of scaling to large hardware multilayer
SNNs.
Liu J, Huang X, Luo Y, Cao Y (2017) An Energy-aware Hybrid Particle Swarm Optimization Algorithm for Spiking Neural Network Mapping, Neural Information Processing 24th International Conference, ICONIP 2017 Guangzhou, China, November 14?18, 2017 Proceedings, Part III pp. 805-815 Springer International Publishing
Recent approaches to improving the scalability of Spiking
Neural Networks (SNNs) have looked to use custom architectures to im-
plement and interconnect the neurons in the hardware. The Networks-
on-Chip (NoC) interconnection strategy has been used for the hardware
SNNs and has achieved a good performance. However, the mapping be-
tween a SNN and the NoC system becomes one of the most urgent chal-
lenges. In this paper, an energy-aware hybrid Particle Swarm Optimiza-
tion (PSO) algorithm for SNN mapping is proposed, which combines the
basic PSO and Genetic Algorithm (GA). A Star-Subnet-Based-2D Mesh
(2D-SSBM) NoC system is used for the testing. Results show that the
proposed hybrid PSO algorithm can avoid the premature convergence
to local optimum, and effectively reduce the energy consumption of the
hardware NoC systems.
Liu S, Zeng J, Gong H, Yang H, Zhai J, Cao Yi, Liu J, Luo Y, Li Y, Maguire L, Ding X (2017) Quantitative analysis of breast cancer diagnosis using a probabilistic modelling approach, Computers in Biology and Medicine 92 pp. 168-175 Elsevier
Background

Breast cancer is the most prevalent cancer in women in most countries of the world. Many computer-aided diagnostic methods have been proposed, but there are few studies on quantitative discovery of probabilistic dependencies among breast cancer data features and identification of the contribution of each feature to breast cancer diagnosis.

Methods

This study aims to fill this void by utilizing a Bayesian network (BN) modelling approach. A K2 learning algorithm and statistical computation methods are used to construct BN structure and assess the obtained BN model. The data used in this study were collected from a clinical ultrasound dataset derived from a Chinese local hospital and a fine-needle aspiration cytology (FNAC) dataset from UCI machine learning repository.

Results

Our study suggested that, in terms of ultrasound data, cell shape is the most significant feature for breast cancer diagnosis, and the resistance index presents a strong probabilistic dependency on blood signals. With respect to FNAC data, bare nuclei are the most important discriminating feature of malignant and benign breast tumours, and uniformity of both cell size and cell shape are tightly interdependent.

Contributions

The BN modelling approach can support clinicians in making diagnostic decisions based on the significant features identified by the model, especially when some other features are missing for specific patients. The approach is also applicable to other healthcare data analytics and data modelling for disease diagnosis.

Luo Yu-Ling, Zhou Rong-Long, Liu Jun-Xiu, Qiu Sen-Hui, Cao Yi (2017) A novel image encryption scheme based on Kepler?s third law and random Hadamard transform, Chinese Physics B 26 (12) 120504 pp. 120504-1 - 120504-15 IOP Publishing
In this paper, a novel image encryption scheme based on Kepler?s third law and random Hadamard transform is
proposed to ensure the security of a digital image. First, a set of Kepler periodic sequences is generated to permutate
image data, which is characteristic of the plain-image and the Kepler?s third law. Then, a random Hadamard matrix is
constructed by combining the standard Hadamard matrix with the hyper-Chen chaotic system, which is used to further
scramble the image coefficients when the image is transformed through random Hadamard transform. In the end, the
permuted image presents interweaving diffusion based on two special matrices, which are constructed by Kepler periodic
sequence and chaos system. The experimental results and performance analysis show that the proposed encrypted scheme
is highly sensitive to the plain-image and external keys, and has a high security and speed, which are very suitable for
secure real-time communication of image data.
Ding X, Cao Y, Zhai J, Maguire L, Li Y, Yang H, Wang Y, Zeng J, Liu S (2017) Bayesian network modelling on data from fine needle aspiration cytology examination for breast cancer diagnosis, Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017) Atlantis Press
The paper employed Bayesian network (BN) modelling approach to discover causal dependencies among different data features of Breast Cancer Wisconsin Dataset (BCWD) derived from openly sourced UCI repository. K2 learning algorithm and k-fold cross validation were used to construct and optimize BN structure. Compared to Na9ve Bayes (NB), the obtained BN presented better performance for breast cancer diagnosis based on fine needle aspiration cytology (FNAC) examination. It also showed that, among the available features, bare nuclei most strongly influences diagnosis due to the highest strength of the influence (0.806), followed by uniformity of cell size, then normal nucleoli. The discovered causal dependencies among data features could provide clinicians to make an accurate decision for breast cancer diagnosis, especially when some features might be missing for specific patients. The approach can be potentially applied to other disease diagnosis.
Luo Yuling, Wan Lei, Harkin Jim, Cao Yi (2018) An efficient, low-cost routing architecture for spiking neural network hardware implementations, Neural Processing Letters 48 (3) pp. 1777-1788 Springer Verlag
The basic processing units in brain are neurons and synapses that are
interconnected in a complex pattern and show many surprised information processing capabilities. The researchers attempt to mimic this efficiency and build
artificial neural systems in hardware device to emulate the key information processing principles of the brain. However, the neural network hardware system has a
challenge of interconnecting neurons and synapses efficiently. An efficient, low-cost
routing architecture (ELRA) is proposed in this paper to provide a communication
infrastructure for the hardware spiking neuron networks (SNN). A dynamic traffic
arbitration strategy is employed in ELRA, where the traffic status weights of input
ports are calculated in real-time according to the channel traffic statuses and the
port with the largest traffic status weight is given a high priority to forward packets. This strategy enables the router to serve congested ports preferentially, which
can balance the overall network traffic loads. Experimental results show the feasibility of ELRA under various traffic scenarios, and the hardware synthesis result
using SAED 90nm technology demonstrates it has a low hardware area overhead
which maintains scalability for large-scale SNN hardware implementations.
Luo Yuling, Zhou Ronglong, Liu Junxiu, Qiu Senhui, Cao Yi (2018) An efficient and self-adapting colour-image encryption algorithm based on chaos and interactions among multiple layers, Multimedia Tools and Applications 77 (20) pp. 26191-26217 Springer Verlag
In this paper, we propose an efficient and self-adapting colour-image encryption algorithm based on chaos and the interactions among multiple red, green and blue (RGB) layers. Our study uses two chaotic systems and the interactions among the multiple layers to strengthen the cryptosystem for the colour-image encryption, which can achieve better confusion and diffusion performances. In the confusion process, we use the novel Rubik?s Cube Scheme (RCS) to scramble the image. The significant advantage of this approach is that it sufficiently destroys the correlation among the different layers of colour image, which is the most important feature of the randomness for the encryption. The theoretical analysis and experimental results show that the proposed algorithm can improve the encoding efficiency, enhances the security of the cipher-text, has a large key space and high key sensitivity, and is also able to resist statistical and exhaustive attacks.
Luo Y, Zhou R, Liu J, Cao Yi, Ding X (2018) A parallel image encryption algorithm based on the
piecewise linear chaotic map and hyper-chaotic map,
Nonlinear Dynamics 93 (3) pp. 1165-1181 Springer Verlag
This paper proposes a parallel digital image
encryption algorithm based on a piecewise linear
chaotic map (PWLCM) and a four-dimensional hyperchaotic
map (FDHCM). Firstly, two decimals are
obtained based on the plain-image and external keys,
using a novel parallel quantification method. They are
used as the initial value and control parameter for
the PWLCM. Then, an encryption matrix and four
chaotic sequences are constructed using the PWLCM
and FDHCM, which control the permutation and diffusion
processes. The proposed algorithm is implemented
and tested in parallel based on a graphics processing
unit device. Numerical analysis and experimental
results show that the proposed algorithm achieves
a high encryption speed and a good security performance,
which provides a potential solution for realtime
image encryption applications.
Luo Y, Zhang D, Liu J, Liu Y, Cao Yi, Ding X (2018) Cryptanalysis of Chaos-based Cryptosystem from the Hardware
Perspective,
International Journal of Bifurcation and Chaos 28 (09) 1850114 World Scientific Publishing
Chaos has been used in cryptography for years and many chaotic cryptographic systems have
been proposed. Their securities are often evaluated by conducting conventional statistical tests,
however few studies have referred to the security issue of the chaotic hardware cryptographic
systems. This paper evaluates the security of the chaotic cryptographic system from a hardware
perspective by using the side channel analysis attack. First, a chaotic block cryptosystem is
designed and implemented based on an Atmel microcontroller. Then the conventional statistical
security tests, including SP 800-22 test, characters frequency test, avalanche test etc., are used to
verify its security performance. In the meantime, the correlation power analysis attack is carried
out for the security evaluation. Experimental results demonstrate that even though the chaotic
cryptographic system can pass the conventional statistical tests, it still has the probability to
be attacked from a hardware perspective using the leaked side channel information including
execution time and power consumption etc. This paper proposes another way to analyze the
security of the chaotic cryptosystem, which can aid designing mechanisms to enhance the security
of the hardware cryptosystems in the future.
Liu Xiaoquan, Cao Yi, Ma Chenghu, Shen Liya (2019) Wavelet-based option pricing: An empirical study, European Journal of Operational Research 272 (3) pp. 1132-1142 Elsevier
In this paper, we adopt a wavelet-based option pricing model and empirically compare
its forecasting and hedging performance with that of other popular models, including the
stochastic volatility model with jumps, the practitioner Black-Scholes model and the neural
network based model. We use daily index options written on the German DAX 30 index
from January 2009 to December 2012. Our results show that the wavelet-based model
compares favorably with all other models except the neural network based one, especially for
long-term options, and that it provides an excellent alternative for valuing option prices. Its
strong performance comes from the powerful ability of the wavelet method in approximating
the risk-neutral moment-generating functions.