2.4 3.

Article

Option Pricing Using LSTM: A

Perspective of Realized Skewness

Yan Liu and Xiong Zhang

Special Issue
Advanced Research in Mathematical Economics and Financial Modelling
Edited by
Prof. Dr. Oana-Ramona Lobonț, Prof. Dr. Chi-Wei Su, Dr. Noja Grațiela Georgiana and
Dr. Weike Zhang

https://doi.org/10.3390/math11020314
 mathematics

Article
Option Pricing Using LSTM: A Perspective of
Realized Skewness
Yan Liu * and Xiong Zhang

School of Economics, Ocean University of China, Qingdao 266100, China

* Correspondence: [email protected]

Abstract: Deep learning has drawn great attention in the financial field due to its powerful ability in
nonlinear fitting, especially in the studies of asset pricing. In this paper, we proposed a long short-term
memory option pricing model with realized skewness by fully considering the asymmetry of asset
return in emerging markets. It was applied to price the ETF50 options of China. In order to emphasize
the improvement of this model, a comparison with a parametric method, such as Black-Scholes (BS),
and machine learning methods, such as support vector machine (SVM), random forests and recurrent
neural network (RNN), was conducted. Moreover, we also took the characteristic of heavy tail into
consideration and studied the effect of realized kurtosis on pricing to prove the robustness of the
skewness. The empirical results indicate that realized skewness significantly improves the pricing
performance of LSTM among moneyness states except for in-the-money call options. Specifically, the
LSTM model with realized skewness outperforms the classical method and other machine learning
methods in all metrics.

Keywords: deep learning; Option pricing; LSTM; realized skewness

MSC: 91G20; 68T07

1. Introduction
Citation: Liu, Y.; Zhang, X. Option
As a momentous derivative financial instrument, the option plays a crucial role in risk
Pricing Using LSTM: A Perspective
management and price discovery. The rapid development of the modern options market
of Realized Skewness. Mathematics
is attributed to the great breakthrough published by Black, Scholes, and Merton [1–3].
2023, 11, 314. https://doi.org/
Thereafter, option pricing has become a hot topic in the derivative financial market.
10.3390/math11020314
As the most famous parametric method for option pricing, the Black-Scholes (BS)
Academic Editors: Oana-Ramona formula is put forward based on five assumptions, among which the most controversial
Lobont, , Noja Grat, iela Georgiana ones are the constant volatility and log normality of the underlying asset return. To
and Weike Zhang overcome the drawbacks of the BS formula, many improvements have been worked out
Received: 21 December 2022
to contribute to this field. For example, against the assumption of constant volatility,
Revised: 2 January 2023 Heston introduced a stochastic volatility option pricing model [4]. Duan [5] assumed
Accepted: 5 January 2023 that the volatility of the underlying asset return followed a GARCH process. With the
Published: 7 January 2023 development of data processing capability, realized vpolatility, which is a non-parametric
volatility measurement based on high-frequency data, has also been incorporated into the
BS pricing framework [6–8].
For the normal assumption, the evidence has been established that the distribution
Copyright: © 2023 by the authors. of asset returns in financial market is asymmetric, especially for emerging financial mar-
Licensee MDPI, Basel, Switzerland. ket [9–11]. The characteristic of heavy tail of financial asset return cannot be ignored
This article is an open access article either [12]. Therefore, some researchers applied skewness for option pricing to get an
distributed under the terms and analytic option pricing formula, achieving more accurate pricing performance [13–15].
conditions of the Creative Commons
Since the Edgeworth expansion has a significant advantage in characterizing the non-
Attribution (CC BY) license (https://
normality distribution of underlying assets [16], Duan et al. [17,18] developed a general
creativecommons.org/licenses/by/
analytical approximation method for pricing European options based on an Edgeworth
4.0/).

Mathematics 2023, 11, 314. https://doi.org/10.3390/math11020314 https://www.mdpi.com/journal/mathematics

Mathematics 2023, 11, 314 2 of 21

series expansion for adjusting skewness and kurtosis of the cumulative asset return in the
framework of GARCH.
Another branch of option pricing studies focuses on non-parametric methods, such
as machine learning. Neural network, Support vector machine (SVM), Random forests,
Extreme gradient boosting (XGBoost), and Light Gradient Boosting Machine (LightGMB)
have achieved empirical success in predicting financial asset price [19–26]. However,
financial data presents feature of high frequency and serial correlation. Due to the great
ability in non-linear fitting and time-series information extraction, a variety of deep-learning
methods have already been applied to predict financial asset price, such as long short-
term memory (LSTM) model [27–30]. Zhang and Huang [31] applied the long short-term
memory recurrent neural network (LSTM-RNN) for hedging. The deep-learning neural
network has also been proven efficient for option pricing [32–36]. For example, attempts
have been made to use deep-learning models on American options [37,38]. Nevertheless,
these methods only focus on refining the structure of the neural network itself, ignoring
the stylized facts of financial asset return, especially the skewness.
In light of the above information, an LSTM neural network [39] with realized skewness
was proposed. The feasibility of implementing this model in option pricing is tested with
the ETF50 options of China. Realized volatility, strike price, maturity, risk-free interest
rate, and underlying asset price, which are usually deployed for derivatives pricing, and
realized skewness, the one considered in our study, have been adopted as our input
features. Furthermore, realized kurtosis has also been considered as one of the input
features when testing the robustness of realized skewness. In comparison to the model
without realized skewness and the model that contains realized skewness and realized
kurtosis, our algorithm containing only realized skewness was applicable to acquire the
intraday price and shows better pricing performance. Moreover, to verify the performance
of the LSTM model when considering realized skewness, benchmark models were exercised
for pricing options [40–45]. Several evaluating metrics, such as mean square error (MSE),
root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage
error (MAPE), were used to test the pricing accuracy of our proposed model.
The remainder of this paper is organized as follows. Section 2 provides a brief back-
ground of the LSTM neural network and recurrent neural network (RNN) and gives the
model structure adopted in this paper. Section 3 conducts an empirical study for pricing
ETF50 options and model comparison. Section 4 provides some concluding remarks.

2. Methodology
2.1. Recurrent Neural Network
The recurrent neural network, which is one of the most popular deep-learning algo-
rithms, is a variant structure of an artificial neural network. It is usually used for processing
time-sequential data due to its ability to capture the relationship between previous period
data and current data. The output features of the previous period are retained during the
training process and are computed as input variables for the next period. The result of the
computation of the t − 1 period of the hidden state will be considered as the input variable
for period t and multiplied by a weight. Then, the activation function maps the hidden
state to the output state. The neurons of each layer are illustrated in Figure 1, where xt is
an input vector at time-step t, ht is the hidden state vector at time-step t, ot is the output at
time-step t, W is the weight from the hidden layer at time-step t − 1 to the hidden layer at
time-step t, U is the weight from the input layer to the hidden layer, and V is the weight
from the hidden layer to the output. The mathematical form of an RNN is given by the
following formulas:
ht = f h (Uxt + Wht−1 ) (1)
ot = f o (Vht ) (2)
Mathematics 2023, 11, 314 𝑜 = 𝑓 (𝑉ℎ ) 3 of 21

𝑓 𝑓 𝑜 = 𝑓 (𝑉ℎ )
𝑓 𝑓
where f h and f o are the activation function. In this paper, ‘ReLU’ function was applied
to describe nonlinear transformation. The use of ‘ReLU’ allows the network to introduce
sparsity on its own, which can greatly increase the training speed.

Figure 1. The structure of a neuron of a recurrent neural network.

For this study, an RNN is proposed that is composed of five simple RNN-layers and
one dense layer. Additionally, there are some dropout-layers included.

2.2. Long Short-Term Memory Neural Network

The LSTM introduced by Hochreiter and Schmidhuber uses a structure called an LSTM
cell to obtain better memory. Meanwhile, in order to avoid gradient explosion and gradient
extinction performed in an RNN, the LSTM uses a gate control mechanism and memory
cells to control information transmission, which greatly enhances the long-term memory
𝑖 ft,
performance [46]. The gate control mechanism consists of an input gate it , forget gate
and output𝑓 gate ot , as shown𝑜 in Figure 2. The input gate determines the input
𝑖 variable
during
𝑓 the current period
𝑜 and the hidden neuron of the previous period to the memory
status of the current period. The forget gate determines the portion to be forgotten from
the input memory cell of the previous period to the memory status of the current period.
The output gate determines the output information from the memory status. Therefore, the
LSTM is specifically designed to learn long-term dependencies.

Figure 2. The structure of neuron of LSTM.

The Equations (3)–(8) portray the update of the memory cells of the LSTM. The
notations of each equation are presented below:
xt is the input vector.
W f , Wi , WC , and Wo are the weight matrices of gate and cell states.
 𝑥
𝑊 𝑊 𝑊 𝑊
Mathematics 2023, 11, 314 𝑏 𝑏 𝑏 𝑏 4 of 21
ℎ
𝑓 𝑖 𝑜
𝐶b f , bi , bC , and bo are bias vectors. 𝐶
𝑓(∙)
ht is the hidden state of the LSTM.
f t , it , and ot are values of forget gate, input gate, and output gate, respectively.
𝑓 = 𝑓(𝑊 ∙ ℎ , 𝑥 + 𝑏 )
Ct is the vector for the cell states and Cet is the temporary vector for the cell states.
f (·) is the activation function.
𝑖 = 𝑓(𝑊 ∙ ℎ , 𝑥 + 𝑏 )
 
f t = f W f ·[ ht−1 , xt ] + b f (3)
𝐶 = 𝑓(𝑊 ∙ ℎ , 𝑥 + 𝑏 )
it = f (Wi ·[ ht−1 , xt ] + bi ) (4)
𝐶 =𝐶 ∙𝑓 +𝑖 ∙𝐶
Cet = f (WC ·[ ht−1 , xt ] + bC ) (5)
𝑜 = 𝑓(𝑊 ∙ ℎ , 𝑥 e+ 𝑏 )
Ct = Ct−1 · f t + it ·Ct (6)
ot = f (ℎWo=·[ h𝑜t−∙1𝑓(𝐶
, xt ])+ bo ) (7)
ht = ot · f (Ct ) (8)
The structure of the LSTM is composed of an input layer, one or more hidden layers,
and an output layer. In addition, the number of neurons in each layer is variant when
considering different problems. Figure 3 shows the network architecture. When processing
an input sequence, the cell states and hidden states are passed through the neurons to
obtain the output. During the training process, the network updates the weights and bias
terms in such a way that it minimizes the loss of the objective function 𝐼 over the entire
training data set, whose ℎ MSE is used in this paper. In Figure 3, In are the input features of
𝑂
our model. hn represents the hidden neurons of hidden layers. It only shows one hidden
layer in Figure 3. O is the output of the network, and in our study, it represents the option
price. The weights of each connection are adjusted according to the feedback error. In
order to construct a pricing model, each layer of the LSTM is stacked with a set of neurons,
as shown in Figure 2. With different amounts of neurons and different number of layers,
the LSTM presents different structures and adapts to different problems. The specified
topology of the LSTM model used in our study is shown in Section 2.3.

Figure 3. Architecture of the LSTM model used in our paper.

2.3. Model Structure

We construct LSTM networks containing five LSTM layers and four Dropout layers,
which are used in our study for pricing the ETF50 options. The Dropout layer can prevent
overfitting. With respect to the numerous factors that affect the prices of options, we
consider the traditional factors that have been approved using the BS model and the
realized skewness and realized kurtosis features proposed in this paper. Then, features that
include spot price, strike price, risk-free rate, time-to-maturity, realized volatility, realized
skewness, and realized kurtosis are selected as input variables. The structure of the LSTM
Mathematics 2023, 11, 314 5 of 21

used in our study is shown in Figure 4. The neural network is trained to retain the prices of
the ETF50 options. Then, the predicted option prices acquired from the network and the
real option prices should be compared to measure the accuracy of the network.

Figure 4. The layers of LSTM model.

In the benchmarks, the structure of the RNN is shown in Figure 5. The overall number
of layers of the LSTM and RNN models are equal, and the hyperparameters of each model
are shown in Table 1.

Figure 5. The layers of the RNN model.

Table 1. Hyperparameter of each model.

LSTM RNN 𝑖
𝑡
Activation function RELU RELU
Loss function 𝑟 , = 100 ∗ (log 𝑝 , MSE
− log 𝑝 , ) 𝑖 = 1, 2 … 𝑁 MSE
Neurons [200, 200, 200, 200, 200, 1] [200, 200, 200, 200, 200, 1]
𝑝 Learning
,
rate 0.001 𝑡 𝑖 0.001
Optimizer Adam Adam
𝑁 = 241

Herein, [200, 200, 200, 200, 200, 1] represents the number of neurons from the first
network layer to the last network layer.
𝑅𝑉 = 𝑟,

𝑁=5
Mathematics 2023, 11, 314 6 of 21

2.4. Computing Realized Higher Moments

We define the intraday log-returns for each interval, and the definition of the ith log
return on day t is given using

rt, i = 100 ∗ (log pt,i − log pt,i−1 ) i = 1, 2 . . . N (9)

where pt,i is the closing price of ETF50 on day t in ith interval. We use one-minute intraday
price so that we have N = 241 in a trading day.
The realized volatility put forward by Andersen and Bollerslev [47] is computed by
summing squares of intraday log-returns

N
RVt = ∑ rt, i 2 (10)
i =1

Meanwhile, the intraday realized volatility, such as the interval [a, b], is a consistent
estimator for the volatility of the instantaneous log-returns process [48]. In this paper, we
consider N = 5.
Because the asymmetry of the distribution of log-returns is prominent in financial
markets, we are interested in computing realized high moments which may have an impact
on the pricing of ETF50 options. We construct a measure of realized skewness and realized
kurtosis constructed by Amaya et al. [49], and the definition of each equation is given by
√
N ∑iN=1 rt,i 3
RDSkewt = (11)
RVt 3/2

N ∑iN=1 rt,i 4
RDKurtt = (12)
RVt 2
It indicates that the return distribution of stock has a left tail that is fatter than the
right tail when there is a negative value of realized skewness and positive values indicate
the opposite.

2.5. Measures of Model Performance

In order to evaluate the option pricing accuracy of realized skewness and different
models, we consider four widely used metrics: mean squared error, root mean squared
error, mean absolute error, and mean absolute percentage error. The smaller the value
of these metrics, the more accurate the option price. The definitions of these metrics are
provided below:
1 n
MSE = ∑ ( pi − p̂i )2 (13)
n i =1
s
1 n
( pi − p̂i )2
n i∑
RMSE = (14)
=1
n
1
MAE =
n ∑ | pi − p̂i | (15)
i =1
n
1 pi − p̂i
MAPE = 100%
n ∑ pi
(16)
i =1

where n is the data number of prediction set, pi is the actual option price, and p̂i is the
predicted price of option.
Of all these metrics, the MAPE reflects the process of comparison with the original
data, which could be more objective. In contrast, the MSE, RMSE, and MAE only mea-
sure the deviation between actual values and estimated values, which are susceptible to
Mathematics 2023, 11, 314 7 of 21

outliers. Thus, we adopted MAPE as the main estimator to assess the accuracy of our
proposed models.

3. Results and Discussion

In this section, we first discuss the details of the China ETF50 options used in our
study, and then use these options as a training set to calibrate our hyperparameters. Our
aim is to show that realized skewness is reliable for option pricing. This is achieved via
a comprehensive testing of the options’ performance on the LSTM model with realized
skewness and the LSTM model without realized skewness. Furthermore, the LSTM model
containing skewness and kurtosis is considered a contrasting model to confirm the ability of
realized skewness on pricing options. In this process, we discuss the respective performance
of different moneyness of call and put options. Then, we also evaluate the pricing validity
between the LSTM model and benchmark models including the RNN, Black-Scholes model,
Support vector machine, and Random forests.

3.1. Summary of the Data

The target we used in this study are the ETF50 options traded in the Shanghai Stock
Exchange, whose underlying asset is the ETF50. They were first traded on 9 February 2015
with a European-style exercise. Meanwhile, the market share of ETF50 options has rapidly
expanded, becoming one of the most important financial derivatives in China. Because
quantitative trading has become prevalent with the development of computer technology,
studying high frequency option pricing is essential for hedging. We use the one-minute
data for the ETF50 options traded from October 2020 to June 2021 for our study, which
were obtained from the Wind database. To get a more accurate pricing performance, we
take away the data whose volume is zero to calibrate our model and eliminate the option
data whose maturity is less than 7 days.
There are one hundred options introduced in our study, among which fifty are call op-
tions and the others are put options. Before passing the data to deep-learning networks, the
options are sorted by moneyness for the sake of contrasting the pricing accuracy of the dif-
ferent moneyness for call and put options. Table 2 describe the moneyness for each option.
A call option should be an in-the-money (ITM) option if moneyness > 1.03, an at-the-money
(ATM) option when 0.97 ≤ moneyness ≤ 1.03, and an out-of-the-money (OTM) option
otherwise. We consider a put option to be an OTM option when moneyness > 1.03, an ATM
option when 0.97 ≤ moneyness ≤ 1.03 , and an ITM option when moneyness < 0.97.

Table 2. Description of moneyness.

State Moneyness
ITM >1.03
Call option ATM 0.97~1.03
OTM <0.97
ITM <0.97
Put option ATM 0.97~1.03
OTM >1.03

As presented in Tables 3 and 4, we have ITM, ATM, OTM for options that are also
divided by call and put. The statistics of all the features of the ETF50 options are shown in
Tables 3 and 4. Herein, “maturity” means the time left to expiration and the moneyness
denotes S/K. Among other features, “r” is the SHIBOR rate and “S” represents the prices
of underlying asset. “K” stands for the strike prices of options.
Mathematics 2023, 11, 314 8 of 21

Table 3. Statistics of ETF50 Call options sorted by moneyness.

Realized Realized Realized

Moneyness r S K Maturity
Volatility Skewness Kurtosis
count 70205 70205 70205 70205 70205 70205 70205
mean 0.0139 3.6119 3.2317 56.4780 0.0411 0.0049 2.2384
ITM std 0.0059 0.1477 0.1499 0.1401 0.0948 1.1394 0.7893
min 0.0061 3.304 2.908 8 0.0006 −2.2361 1
max 0.0328 4.096 3.4 237 3.9760 2.2361 5
count 83637 83637 83637 83637 83637 83637 83637
mean 0.01442 3.6181 3.4932 58.0846 0.0345 0.0199 2.2216
ATM std 0.0063 0.1529 0.0949 0.1374 0.0771 1.1112 0.777
min 0.0061 3.304 3.253 8 0.0006 −2.2361 1
max 0.0328 4.096 3.6 237 3.9760 2.2361 5
count 222532 222532 222532 222532 222532 222532 222532
mean 0.0163 3.6242 3.7427 69.1648 0.0338 0.0151 2.2193
OTM std 0.0063 0.1569 0.122 0.1594 0.0778 1.1095 0.7772
min 0.0061 3.304 3.45 8 0.0006 −2.2361 1
max 0.0328 4.096 3.9 237 3.976 2.2361 5

Table 4. Statistics of ETF50 Put options sorted by moneyness.

Realized Realized Realized

Moneyness r S K Maturity
Volatility Skewness Kurtosis
count 153988 153988 153988 153988 153988 153988 153988
mean 0.0174 3.6841 3.7128 58.6633 0.0397 0.0071 2.2123
ITM std 0.0062 0.1529 0.1344 0.1389 0.0939 1.1093 0.7664
min 0.0061 3.304 3.45 8 0.0006 −2.2361 1
max 0.0328 4.096 3.9 237 3.976 2.2361 5
count 103716 103716 103716 103716 103716 103716 103716
mean 0.0154 3.6317 3.4596 64.8511 0.0346 0.0192 2.2207
ATM std 0.0064 0.1576 0.1134 0.1463 0.0813 1.1099 0.7756
min 0.0061 3.304 3.253 8 0.0006 −2.2361 1
max 0.0328 4.096 3.6 236 3.976 2.2361 5
count 145085 145085 145085 145085 145085 145085 145085
mean 0.015 3.5979 3.1774 77.7259 0.0354 0.0164 2.2283
OTM std 0.0062 0.1502 0.1575 0.1671 0.0883 1.1194 0.7853
min 0.0061 3.304 2.908 8 0.0007 −2.2361 1
max 0.0328 4.096 3.4 237 3.976 2.2361 5

Another problem arises because the time-to-maturity has a different magnitude. As a

result, the weight adjustment of the network will be overwhelmed by the larger values of
an input variable. To prevent larger input variables from becoming dominant, we divide
the maturity by 365.

3.2. Pricing Performance of Long Short-Term Memory Model

3.2.1. The Effective Analysis of Realized Skewness
We investigate whether deep-learning models can be applied to estimate given option
data well, which is key to the pricing performance of a deep-learning model given market
information. We use the intraday option prices to calibrate each model and get the optimal
hyperparameters by minimizing the loss function. We then use ETF50 options to compare
the performance of the LSTM that possesses realized skewness as an input feature with the
LSTM that consists only of five normal features (r, S, K, maturity, and Realized volatility).
Additionally, we use benchmark models to emphasize the pricing ability of LSTM. The
LSTM model is compared with BS, SVM, Random forests, and an RNN. The ETF50 options
data are established in chronological order from 2020 to 2021.
Mathematics 2023, 11, 314 9 of 21

Table 5 presents the pricing errors of the LSTM without realized skewness, and Table 6
presents the pricing errors of the LSTM containing realized skewness on ETF50 options.
They indicate that the errors of call options and put options are smaller for the LSTM with
realized skewness except for in-the-money call options. When moneyness is not considered,
we find that the ETF50 option pricing model that includes realized skewness is decreased
in MSA by 15.22% and 29.03% for a call option and put option, respectively. In terms of
root mean squared error, the ETF50 option pricing model that includes realized skewness
is reduced by 15.26% for a call option and 16.12% for a put option. Additionally, there
is a decrease in the mean absolute error of 14.37% and 16.46% for call options and put
options, respectively. Further, MAPE decreases by 9.91% and 30.21% for the call option
and put option, respectively, which indicates the excellent ability of the realized skewness
for modeling pricing options. The empirical results indicate that, from the perspective of
realized skewness, the LSTM with realized skewness as one of the input features performs
more excellently than the LSTM without realized skewness across all metrics. This implies
that our proposed model has a higher accuracy in option pricing.

Table 5. Pricing error of LSTM without realized skewness.

Metrics Call Options Put Options

ITM ATM OTM ITM ATM OTM
MSE 0.0067 0.0289 0.0261 0.0442 0.0047 0.0019
RMSE 0.8197 1.7003 1.6149 2.1027 0.6876 0.4307
MAE 0.6437 1.5225 1.3905 1.8732 0.4064 0.2506
MAPE 1.1611 5.2866 28.0592 25.1675 20.1217 46.2594
Note: All values are multiplied by a factor of 100.

Table 6. Pricing error of LSTM with realized skewness.

Metrics Call Options Put Options

ITM ATM OTM ITM ATM OTM
0.0118 0.006 0.015 0.0207 0.0036 0.0017
MSE
−76.12% 79.24% 42.53% 53.17% 23.40% 10.53%
1.0875 0.7761 1.2257 1.438 0.6035 0.4113
RMSE
−32.67% 54.36% 24.10% 31.61% 12.23% 4.50%
0.9053 0.6253 1.0454 1.3198 0.3542 0.2331
MAE
−40.64% 58.96% 24.82% 29.54% 12.84% 6.98%
1.791 2.3868 19.8898 16.0634 16.7579 28.8013
MAPE
−54.25% 54.85% 29.11% 36.17% 16.72% 37.74%
Note: All values are multiplied by a factor of 100. The second line of each item is the percentage reduction per
metric compared with LSTM without realized skewness. A negative value means the metric is higher than the
previous value.

In the process of option pricing, our empirical results demonstrate that the realized
skewness has a significant impact on the accuracy of the option pricing. Considering the
performance of the LSTM with realized skewness, put options have a higher improvement
in accuracy than call options in each metric. The skewness has an effect on the return rate
of the underlying asset, which leads to differences in accuracy.
On the moneyness side, compared with the LSTM without realized skewness, the
LSTM with realized skewness demonstrates the best accuracy for ITM options, while call
options and put options are accurately priced in a majority of the moneyness states.
The effectiveness of the LSTM model with realized skewness is robust in option pricing
except for the ITM call option. As we tested based on different maturity and moneyness of
ETF50 options, the performance of the LSTM shows that call options have smaller errors
than put options in ITM, ATM, and OTM, respectively. This is consistent with the general
pattern that the accuracy of the put option pricing model is lower than that of the call
Mathematics 2023, 11, 314 10 of 21

option pricing model. The results of the ETF50 option pricing test indicate that the realized
skewness can effectively improve the accuracy of deep learning for option pricing.

3.2.2. The Effective Analysis of Realized Kurtosis

To verify the effectiveness of realized kurtosis on pricing options, we consider the
LSTM model that contains realized skewness and realized kurtosis compared to the model
that contains only normal features and the model that includes realized skewness. Table 7
presents the errors of realized kurtosis when applied to option pricing after training the
model using ETF50 option data.

Table 7. Pricing error of LSTM with realized skewness and realized kurtosis.

Metrics Call Options Put Options

ITM ATM OTM ITM ATM OTM
0.0138 0.0054 0.0282 0.0305 0.0045 0.0015
MSE
−16.64% 9.31% −87.94% −47.46% −24.81% 10.70%
1.1732 0.7377 1.6790 1.7471 0.6703 0.3896
RMSE
−7.88% 4.95% −36.99% −21.50% −11.07% 5.27%
0.9242 0.5917 1.4537 1.5390 0.3751 0.2196
MAE
−2.09% 5.37% −39.06% −16.61% −5.90% 5.81%
1.6019 2.3151 29.0479 16.6420 16.7752 29.6484
MAPE
10.56% 3.01% −46.04% −3.60% −0.10% −2.94%
Note: All values are multiplied by a factor of 100. The second line of each item is the percentage reduction per
metric compared with the LSTM containing realized skewness. A negative value means the metric is higher than
the previous value.

As shown in Table 7, the values of the MAPE metric increase in the majority of
moneyness states. When considering the MAPE of put options, the value of the ITM option
increases 3.6%. For the ATM option, the value is 0.1% and 2.94% on OTM. Especially, the
pricing error increases 46.04% in the OTM option. The results of the LSTM option pricing
model that uses realized skewness and realized kurtosis show that it performs poorly
in each moneyness category of put options when compared with the model containing
only realized skewness. Call options also perform poorly in OTM. When considering ITM
and ATM call options, the model improves the pricing accuracy of ETF50 options slightly.
The results are consistent with the fact that kurtosis is relatively weak on pricing options
compared with skewness.
Figure 6 shows the comparison of MAPE among the normal model with of five normal
features (the “Original”), the LSTM with realized skewness (the “RDSkew”), and the LSTM
with realized skewness and realized kurtosis (the “RDSkew&RDKurt”). As shown in
Figure 6, the pricing model with realized skewness has a superior performance in the
majority of moneyness states. As for the ITM call option, the model that does not consider
realized skewness and realized kurtosis, the Original, performs with the best accuracy.
As shown in Figures 7–12, the option pricing performance of the LSTM with realized
skewness (RDSkew) (a) presents more accuracy than that of the LSTM without realized
skewness (Original) (b). It also outperforms the model that contains realized skewness and
realized kurtosis (RDSkew&RDKurt) (c) in most moneyness states.
Mathematics 2023, 11, 314 11 of 21

Figure 6. The comparison of the MAPE of different models considering realized skewness and
realized kurtosis.

Figure 7. The performance of ITM call options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.

Figure 8. The performance of ATM call options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.
Mathematics 2023, 11, 314 12 of 21

Figure 9. The performance of OTM call options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.

Figure 10. The performance of ITM put options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.

Figure 11. The performance of ATM put options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.
Mathematics 2023, 11, 314 13 of 21

Figure 12. The performance of OTM put options in different features (a) represents the LSTM with
realized skewness, (b) represents the LSTM without realized skewness, (c) represents the LSTM with
realized skewness and realized kurtosis.

3.3. Pricing Performance of Benchmark Models

The results of benchmark models are measured with the metrics obtained on the
dataset with realized skewness, which is an important variable for option pricing. The
BS option pricing model, SVM, and Random forests, including 200 decision trees, have
been used for− comparison with the LSTM − model, and, − thus, their−results are summarized to
confirm the pricing performance of the LSTM. Nevertheless, the results obtained with the
−
benchmark machine − used as an
learning models are − indicator of− the possible error range.
The first conclusion is that the quality of pricing with the benchmark models varies
considerably− across the different states
− of moneyness− for options. − ITM and ATM options
are much more accurate compared with OTM options when it concerns the call option in
− put option,− ITM options
all of the benchmarks. In the terms of the − have a smaller
− deviation
than ATM and OTM options. Both call and put OTM options are priced with a maximum
percentage deviation. For call options and put options, the LSTM model with realized
skewness performs the best, followed by the Random forests model.
When it comes to the pricing accuracy of the LSTM model with realized skewness,
Tables 8–10 reveal that the LSTM model presented the most excellent pricing performance
except for ITM put options, with remarkable nonlinear fitting ability. The BS model
provides the least reliable pricing due to the maximum values of metrics. The ITM call
options are priced using the LSTM model with an MAPE close to 0.01791, 0.023868 for ATM
call options, and around 0.198898 for OTM. For call options priced using LSTM, the MAPE
decreases by 98.21%, 97.55%, and 92.68% compared with the BS model with the ITM, ATM,
and OTM moneyness states, respectively. Those decreases are 67.80%, 84.23%, and 73.75%
when compared with the SVM model and 0.65%, 49.16%, and 13.44% when compared with
the Random forests model. Compared with the RNN model, which is most similar to the
LSTM model, the MAPE decreases by 83.26% for ITM call options, 82.74% for ATM call
options and 72.57% for OTM call options. Similarly, the metric is smallest with put options
priced using the LSTM model. When compared with the BS model, the LSTM optimization
has 75.01%, 83.93%, and 73.31% in terms of the ITM, ATM, and OTM options. They are
78.87%, 98.18%, and 99.13% compared with SVM model, −37.07%, 44.88%, and 16.44%
compared with the Random forests model, and 71.47%, 90.35%, and 84.33% compared with
the RNN model. In terms of the moneyness of call and put options, ITM options have the
most accurate pricing quality regardless of the pricing model.
Mathematics 2023, 11, 314 14 of 21

Table 8. Pricing error of ITM options estimated using different models when using realized skewness.

ITM Call Options ITM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 33.6885 58.0418 55.9973 99.9041 0.4037 6.3540 5.7960 64.2859
SVM 0.1221 3.4946 2.8661 5.5627 0.3562 5.9681 5.7673 76.0187
RF 0.0209 1.4474 0.9829 1.8028 0.0113 1.0631 0.8555 11.7190
RNN 0.5544 7.4460 6.2965 10.6978 0.2093 4.5747 4.3433 56.2957
LSTM 0.0118 1.0875 0.9053 1.7910 0.0207 1.4380 1.3198 16.0634
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.

Table 9. Pricing error of ATM options estimated using different models when using realized skewness.

ATM Call Options ATM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 0.3303 5.7471 4.1122 97.2872 0.1095 3.3095 2.2106 104.2794
SVM 0.1257 3.5457 3.0895 15.1358 0.5718 7.5617 7.4347 921.8113
RF 0.0257 1.6023 1.2072 4.6944 0.0064 0.7989 0.5151 30.4049
RNN 0.1764 4.1998 3.6286 13.8309 0.0458 2.1405 2.0417 173.6328
LSTM 0.0060 0.7761 0.6253 2.3868 0.0036 0.6035 0.3542 16.7579
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.

Table 10. Pricing error of OTM options estimated using different models when using
realized skewness.

OTM Call Options OTM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 2.2385 14.9615 12.1928 271.6490 0.0154 1.2413 0.7371 107.8957
SVM 0.2772 5.2650 4.8966 75.7476 0.8353 9.1395 9.1124 3293.3315
RF 0.0627 2.5038 1.8247 22.9774 0.0023 0.4832 0.2845 34.4681
RNN 0.1661 4.0753 3.8056 72.5007 0.0048 0.6939 0.6531 183.8504
LSTM 0.0150 1.2257 1.0454 19.8898 0.0017 0.4113 0.2331 28.8013
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.

For the sake of robustness, a review of a set of different models has been conducted.
We train the model with realized skewness and realized kurtosis for comparison. When con-
taining realized kurtosis, LSTM also has the most accurate pricing capability. Tables 11–13
show that LSTM presents the lowest metrics except for ITM put options.

Table 11. Pricing error of ITM options estimated using different models when using realized skewness
and realized kurtosis.

ITM Call Options ITM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 33.6885 58.0418 55.9973 99.9041 0.4037 6.3540 5.7960 64.2859
SVM 0.1226 3.5016 2.8688 5.6109 0.3513 5.9267 5.7186 75.6203
RF 0.0208 1.4406 0.9812 1.7970 0.0112 1.0576 0.8497 11.6567
RNN 0.5987 7.7373 6.5175 11.1190 0.3030 5.5043 5.3030 69.5781
LSTM 0.0138 1.1732 0.9242 1.6019 0.0305 1.7471 1.5390 16.6420
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.
Mathematics 2023, 11, 314 15 of 21

Table 12. Pricing error of ATM options estimated using different models when using realized
skewness and realized kurtosis.

ATM Call Options ATM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 0.3303 5.7471 4.1122 97.2872 0.1095 3.3095 2.2106 104.2794
SVM 0.1139 3.3744 2.9022 14.3229 0.5596 7.4806 7.3462 912.8136
RF 0.0253 1.5915 1.2008 4.6725 0.0058 0.7584 0.4925 29.7101
RNN 0.1815 4.2605 3.6802 14.1544 0.0472 2.1731 2.1188 200.7604
LSTM 0.0054 0.7377 0.5917 2.3151 0.0045 0.6703 0.3751 16.7752
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.

Table 13. Pricing error of OTM options estimated using different models when using realized
skewness and realized kurtosis.

OTM Call Options OTM Put Options

Models
MSE RMSE MAE MAPE MSE RMSE MAE MAPE
BS 2.2385 14.9615 12.1928 271.6490 0.0154 1.2413 0.7371 107.8957
SVM 0.2856 5.3446 4.9778 77.0127 0.8353 9.1395 9.1124 3293.3115
RF 0.0628 2.5053 1.8241 23.0268 0.0024 0.4849 0.2853 34.4997
RNN 0.2163 4.6503 4.3962 83.6558 0.0091 0.9544 0.8765 238.5260
LSTM 0.0282 1.6790 1.4537 29.0479 0.0015 0.3896 0.2196 29.6484
Note: ‘RF’ stands for Random forests model and all values are multiplied by a factor of 100.

Figures 13–18 illustrate the different pricing performance of LSTM (a) and benchmark
models (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random
forests model, and (e) stands for the RNN model when realized skewness is considered.
The pictures demonstrate that the prices using the LSTM model with realized skewness are
closest to the real prices.

Figure 13. The pricing performance of ITM call options on each model, (a) stands for the LSTM
model, (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Ran-dom forests
model, (e) stands for the RNN model.
Mathematics 2023, 11, 314 16 of 21

Figure 14. The pricing performance of ATM call options on each model (a) stands for the LSTM
model, (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random forests
model, (e) stands for the RNN model.

Figure 15. The pricing performance of OTM call options on each model (a) stands for the LSTM
model, (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random forests
model, (e) stands for the RNN model.
Mathematics 2023, 11, 314 17 of 21

Figure 16. The pricing performance of ITM put options on each model (a) stands for the LSTM model,
(b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random forests model,
(e) stands for the RNN model.

Figure 17. The pricing performance of ATM put options on each model (a) stands for the LSTM
model, (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random forests
model, (e) stands for the RNN model.
Mathematics 2023, 11, 314 18 of 21

Figure 18. The pricing performance of OTM put options on each model (a) stands for the LSTM
model, (b) stands for the BS model, (c) stands for the SVM model, (d) stands for the Random forests
model, (e) stands for the RNN model.

The obtained results suggest that the LSTM model, which consists of realized skewness,
has outstanding pricing performance for ETF50 options. So far, the price provided using
the LSTM model with realized skewness is more reliable than that from BS, SVM, Random
forest, and RNN models, as the resulting errors are lowest for the LSTM model with
realized skewness. Thus, it confirms the ability of realized skewness in option pricing with
a deep-learning model.

4. Conclusions
In this study, an LSTM model with realized skewness has been proposed for option
pricing. We validated the efficiency and accuracy of the proposed model by pricing the
ETF50 options of China from 2020 to 2021. The deep-learning models were calibrated in a
data-driven approach, which means that accuracy metrics can be used to tune the LSTM
model. To check the pricing ability, the data is split into a training sample, a validation
sample for adjusting hyperparameters, and a test sample for verifying the accuracy of
option prices. Then, in order to confirm the pricing performance of the LSTM model with
realized skewness, BS, Support vector machine, Random forest, and RNN models with
realized skewness were considered as benchmarks. To confirm the robustness of LSTM,
we also constructed the model containing realized skewness and realized kurtosis for
comparison. The results are presented for call and put options and are separated by three
different moneyness states.
The results obtained from the empirical analysis demonstrate that the pricing accuracy
can be improved when realized skewness serves as an input feature, except for ITM call
options. One of the possibilities for dealing with the difficulties met by ITM call options
would be to develop different models for this characteristic. However, it performs poorly
in the model that contains realized skewness and realized kurtosis, compared with the
model only containing realized skewness, which confirms the fact that skewness has more
significant ability on pricing options when compared with kurtosis. In terms of all metrics,
Mathematics 2023, 11, 314 19 of 21

the LSTM model with realized skewness reduces the pricing error by 4.50–79.24%, which
confirms the fact that the distribution of real market option data performs better with
skewness. As to how we approach the problem, the constructed model improves option
pricing significantly compared with benchmarks. Especially, an LSTM model with realized
skewness shows the best overall performance.
From the perspective of each model, the LSTM model has certain improvement in
option pricing task compared with the other types of models in two aspects of comparison:
realized skewness, and realized skewness and realized kurtosis. For the realized skewness
dimension, by comparing LSTM, RNN, BS, SVM, and Random forests that contain realized
skewness, the LSTM model shows a strong extracting ability. As for the realized skewness
and realized kurtosis aspects, the LSTM model improves the accuracy of option pricing in
most moneyness states.
For future research, some new features could be applied to a deep-learning neural
network. For example, new market contingencies, such as Covid-19, which may influence
investors’ behavior, could be quantified to price options. Furthermore, one could apply
the proposed model to price other financial derivatives, such as Asian options. In addition,
more effort could be committed to explore the interpretability of a long short-term neural
network when applying it to solve financial problems.

Author Contributions: Conceptualization, Y.L. and X.Z.; methodology, Y.L. and X.Z.; writing—
original draft preparation, X.Z.; writing—review and editing, Y.L. and X.Z.; funding acquisition, Y.L.
All authors have read and agreed to the published version of the manuscript.
Funding: This research was funded by the National Natural Science Foundation of China (72003180)
and the Ministry of education of Humanities and Social Science project (18YJA790113).
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: The data presented in this study are available on request from the
corresponding author.
Conflicts of Interest: The authors declare no conflict of interest.

Abbreviation

LSTM Long short-term memory

BS Black-Scholes
ETF Exchange Traded Funds
SVM Support vector machine
RNN Recurrent neural network
GARCH Generalized Auto Regressive Conditional Heteroskedasticity
XGBoost Extreme gradient boosting
LightGBM Light gradient boosting machine
LSTM-RNN Long short-term memory recurrent neural network
ReLU Rectified linear unit
MSE Mean squared error
RMSE Root mean squared error
MAE Mean absolute error
MAPE Mean absolute percentage error
RV Realized volatility
RDSkew Realized skewness
RDKurt Realized kurtosis
ITM In-the-money
ATM At-the-money
OTM Out-of-the-money
RF Random forests
Mathematics 2023, 11, 314 20 of 21

References
1. Black, F.; Scholes, M. The pricing of options and corporate liabilities. J. Political Econ. 1973, 81, 637–654. [CrossRef]
2. Merton, R.C. Theory of rational option pricing. Bell J. Econ. Manag. Sci. 1973, 4, 141–183. [CrossRef]
3. Merton, R.C. Option pricing when underlying stock returns are discontinuous. J. Financ. Econ. 1976, 3, 125–144. [CrossRef]
4. Heston, S.L. A closed-form solution for options with stochastic volatility with applications to bond and currency options. Rev.
Financ. Stud. 1993, 6, 327–343. [CrossRef]
5. Duan, J.C. The GARCH option pricing model. Math. Financ. 1995, 5, 13–32. [CrossRef]
6. Corsi, F.; Fusari, N.; La Vecchia, D. Realizing smiles: Options pricing with realized volatility. J. Financ. Econ. 2013, 107, 284–304.
[CrossRef]
7. Christoffersen, P.; Feunou, B.; Jacobs, K.; Meddahi, N. The economic value of realized volatility: Using high-frequency returns for
option valuation. J. Financ. Quant. Anal. 2014, 49, 663–697. [CrossRef]
8. Huang, Z.; Wang, T.; Hansen, P.R. Option pricing with the realized GARCH model: An analytical approximation approach. J.
Futures Mark. 2017, 37, 328–358. [CrossRef]
9. Harvey, C.R.; Siddique, A. Conditional skewness in asset pricing tests. J. Financ. 2000, 55, 1263–1295. [CrossRef]
10. Bakshi, G.; Madan, D. A theory of volatility spreads. Manag. Sci. 2006, 52, 1945–1956. [CrossRef]
11. Ghysels, E.; Plazzi, A.; Valkanov, R. Why invest in emerging markets? The role of conditional return asymmetry. J. Financ. 2016,
71, 2145–2192. [CrossRef]
12. Conrad, J.; Dittmar, R.F.; Ghysels, E. Ex ante skewness and expected stock returns. J. Financ. 2013, 68, 85–124. [CrossRef]
13. Christoffersen, P.; Elkamhi, R.; Feunou, B.; Jacobs, K. Option valuation with conditional heteroskedasticity and nonnormality. Rev.
Financ. Stud. 2010, 23, 2139–2183. [CrossRef]
14. Christoffersen, P.; Heston, S.; Jacobs, K. Option valuation with conditional skewness. J. Econom. 2006, 131, 253–284. [CrossRef]
15. Kim, S.; Lee, G.; Park, Y.J. Skewness versus kurtosis: Implications for pricing and hedging options. Asia Pac. J. Financ. Stud. 2017,
46, 903–933. [CrossRef]
16. Jarrow, R.; Rudd, A. Approximate option valuation for arbitrary stochastic process. J. Financ. Econ. 1982, 10, 347–369. [CrossRef]
17. Duan, J.C.; Simonato, J.G. American option pricing under GARCH by a Markov chain approximation. J. Econ. Dyn. Control 2001,
25, 1689–1718. [CrossRef]
18. Duan, J.; Gauthier, G.; Simonato, J.; Sasseville, C. Approximating the GJR-GARCH and EGARCH option pricing models
analytically. J. Comput. Financ. 2006, 9, 41–69. [CrossRef]
19. Malliaris, M.; Salchenberger, L. A neural network model for estimating option prices. Appl. Intell. 1993, 3, 193–206. [CrossRef]
20. Gradojevic, N.; Gencay, R.; Kukolj, D. Option pricing with modular neural networks. IEEE Trans. Neural Netw. 2009, 20, 626–637.
[CrossRef]
21. Quek, C.; Pasquier, M.; Kumar, N. A novel recurrent neural network-based prediction system for option trading and hedging.
Appl. Intell. 2008, 29, 138–151. [CrossRef]
22. Liang, X.; Zhang, H.; Xiao, J.; Chen, Y. Improving option price forecasts with neural networks and support vector regressions.
Neurocomputing 2009, 72, 3055–3065. [CrossRef]
23. Park, H.; Kim, N.; Lee, J. Parametric models and non-parametric machine learning models for predicting option prices: Empirical
comparison study over KOSPI 200 Index options. Expert Syst. Appl. 2014, 41, 5227–5237. [CrossRef]
24. Das, S.P.; Padhy, S. A new hybrid parametric and machine learning model with homogeneity hint for European-style index
option pricing. Neural Comput. Appl. 2017, 28, 4061–4077. [CrossRef]
25. Jang, H.; Lee, J. Generative Bayesian neural network model for risk-neutral pricing of American index options. Quant. Financ.
2019, 19, 587–603. [CrossRef]
26. Ivas, cu, C. Option pricing using machine learning. Expert Syst. Appl. 2021, 163, 113799. [CrossRef]
27. Fischer, T.; Krauss, C. Deep learning with long short-term memory networks for financial market predictions. Eur. J. Oper. Res.
2018, 270, 654–669. [CrossRef]
28. Selvin, S.; Vinayakumar, R.; Gopalakrishnan, E.A.; Menon, V.K.; Soman, K.P. Stock price prediction using LSTM, RNN and
CNN-sliding window model. In Proceedings of the 2017 International Conference on Advances in Computing, Communications
and Informatics (ICACCI), Udupi, India, 13–16 September 2017.
29. Hu, Y.; Sun, X.; Nie, X.; Li, Y.; Liu, L. An enhanced LSTM for trend following of time series. IEEE Access 2019, 7, 34020–34030.
[CrossRef]
30. Pang, X.; Zhou, Y.; Wang, P.; Lin, W.; Chang, V. An innovative neural network approach for stock market prediction. J. Supercomput.
2020, 76, 2098–2118. [CrossRef]
31. Zhang, J.; Huang, W. Option hedging using LSTM-RNN: An empirical analysis. Quant. Financ. 2021, 21, 1753–1772. [CrossRef]
32. Chou, C.; Liu, J.; Chen, C.; Huang, S. Deep learning in model risk neutral distribution for option pricing. In Proceedings of the
2019 IEEE International Conference on Agents (ICA), Jinan, China, 18–21 October 2019; pp. 95–98.
33. Culkin, R.; Das, S.R. Machine learning in finance: The case of deep learning for option pricing. J. Investig. Manag. 2017, 15, 92–100.
34. Jang, J.H.; Yoon, J.; Kim, J.; Gu, J.; Kim, H.Y. DeepOption: A novel option pricing framework based on deep learning with fused
distilled data from multiple parametric methods. Inf. Fusion 2021, 70, 43–59. [CrossRef]
35. Arin, E.; Ozbayoglu, A.M. Deep Learning Based Hybrid Computational Intelligence Models for Options Pricing. Comput. Econ.
2022, 59, 39–58. [CrossRef]
Mathematics 2023, 11, 314 21 of 21

36. Qian, L.; Zhao, J.; Ma, Y. Option Pricing Based on GA-BP neural network. In Proceedings of the 8th International Conference on
Information Technology and Quantitative Management (ITQM 2020 & 2021): Developing Global Digital Economy After Covid-19,
Chengdu, China, 9–11 July 2021; Volume 199, pp. 1340–1354.
37. Becker, S.; Cheridito, P.; Jentzen, A.; Welti, T. Solving high-dimensional optimal stopping problems using deep learning. Eur. J.
Appl. Math. 2021, 32, 470–514. [CrossRef]
38. Fu, W.; Hirsa, A. Fast pricing of American options under variance gamma. J. Comput. Financ. 2021, 25, 29–49. [CrossRef]
39. Hochreiter, S.; Schmidhuber, J. Long Short-Term Memory. Neural Comput. 1997, 9, 1735–1780. [CrossRef]
40. Breimanl, L. Random forests. Mach. Learn. 2001, 45, 5–32. [CrossRef]
41. Ho, T.K. Random decision forests. In Proceedings of the 3rd International Conference on Document Analysis and Recognition,
Montreal, QC, Canada, 14–16 August 1995; Volume 1, pp. 278–282.
42. Cortes, C.; Vladimir, V. Support-Vector Networks. Mach. Learn. 1995, 20, 273–297. [CrossRef]
43. Khemchandani, R.; Goyal, K.; Chandra, S. TWSVR: Regression via Twin Support Vector Machine. Neural Netw. 2016, 74, 14–21.
[CrossRef]
44. Hsu, C.-W.; Lin, C.-J. A comparison of methods for multiclass support vector machines. IEEE Trans. Neural Netw. 2002, 13,
415–425.
45. Saad, E.W.; Prokhorov, D.V.; Wunsch, D.N. Comparative study of stock trend prediction using time delay, recurrent and
probabilistic neural networks. IEEE Trans. Neural Netw. 1998, 9, 1456–1470. [CrossRef] [PubMed]
46. Van Houdt, G.; Mosquera, C.; Napoles, G. A review on the long short-term memory model. Artif. Intell. Rev. 2020, 53, 5929–5955.
[CrossRef]
47. Andersen, T.; Bollerslev, T. Towards a unified framework for high and low frequency return volatility modeling. Stat. Neerl. 1998,
52, 273–302. [CrossRef]
48. Degiannakis, S.; Floros, C. Intra-day realized volatility for European and USA stock indices. Glob. Financ. J. 2016, 29, 24–41.
[CrossRef]
49. Amaya, D.; Christoffersen, P.; Jacobs, K.; Vasquez, A. Does realized skewness predict the cross-section of equity returns? J. Financ.
Econ. 2015, 118, 135–167. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.