No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Stock Price Prediction by Using Hybrid Sequential Generative Adversarial Networks
... In He and Kita's research work [16], stock price prediction is conducted through a hybrid sequential model of Generative Adversarial Networks (GANs) incorporating distinct Recurrent Neural Networks (RNN, LSTM, GRU). The study's primary aim was to forecast stock prices within the S&P 500 dataset. ...
... Fig. 1. shows the architecture of the proposed model. As stated in [16], the combination of LSTM and RNN has demonstrated superior performance compared to Deep Neural Networks (DNNs) and basic RNN models in tasks such as predicting stock movements or speech recognition. Notably, conventional DNNs are limited to modeling fixedsized sliding windows, lacking interdependence on preceding time steps. ...
... Vuletić et al. [93] investigated GANs for probability forecasting of financial time series, using a novel economics-driven loss function in the generator. Ljung [94] assessed CTGAN's ability to generate synthetic data, while He and Kita [95] employed a hybrid sequential GAN model with three training strategies using S&P500 data. ...
The integration of generative AI (GAI) into the financial sector has brought about significant advancements, offering new solutions for various financial tasks. This review paper provides a comprehensive examination of recent trends and developments at the intersection of GAI and finance. By utilizing an advanced topic modeling method, BERTopic, we systematically categorize and analyze existing research to uncover predominant themes and emerging areas of interest. Our findings reveal the transformative impact of finance-specific large language models (LLMs), the innovative use of generative adversarial networks (GANs) in synthetic financial data generation, and the pressing necessity of a new regulatory framework to govern the use of GAI in the finance sector. This paper aims to provide researchers and practitioners with a structured overview of the current landscape of GAI in finance, offering insights into both the opportunities and challenges presented by these advanced technologies.
... Vuletić et al. [90] investigated GANs for probability forecasting of financial time series, using a novel economics-driven loss function in the generator. Ljung [91] assessed CTGAN's ability to generate synthetic data, while He and Kita [92] employed a hybrid sequential GANs model with three training strategies using S&P500 data. ...
The integration of generative AI (GAI) into the financial sector has brought about significant advancements, offering new solutions for various financial tasks. This review paper provides a comprehensive examination of recent trends and developments at the intersection of GAI and finance. By utilizing an advanced topic modeling method, BERTopic, we systematically categorize and analyze existing research to uncover predominant themes and emerging areas of interest. Our findings reveal the transformative impact of finance-specific large language models (LLMs), the innovative use of generative adversarial networks (GANs) in synthetic financial data generation, and the pressing necessity of a new regulatory framework to govern the use of GAI in the finance sector. This paper aims to provide researchers and practitioners with a structured overview of the current landscape of GAI in finance, offering insights into both the opportunities and challenges presented by these advanced technologies.
... Year Application [159] 2018 Stock market [160] 2019 Traffic forecasting [154] 2019 Lorenz/Mackey-Glass/Internet Traffic data [161] 2019 Medicine expenditure [162] 2019 Electricity load [163] 2020 Stock price [164] 2020 Long-term benchmark data sets (see Section 6.2) [165] 2020 Soil temperature [166] 2021 Stock market/Energy production/EEG/Air quality [156] 2021 Internet Traffic data [167] 2021 Store Item Demand/Internet Traffic/Meteorological data [168] 2021 ...
A time series is a sequence of time-ordered data, and it is generally used to describe how a phenomenon evolves over time. Time series forecasting, estimating future values of time series, allows the implementation of decision-making strategies. Deep learning, the currently leading field of machine learning, applied to time series forecasting can cope with complex and high-dimensional time series that cannot be usually handled by other machine learning techniques. The aim of the work is to provide a review of state-of-the-art deep learning architectures for time series forecasting, underline recent advances and open problems, and also pay attention to benchmark data sets. Moreover, the work presents a clear distinction between deep learning architectures that are suitable for short-term and long-term forecasting. With respect to existing literature, the major advantage of the work consists in describing the most recent architectures for time series forecasting, such as Graph Neural Networks, Deep Gaussian Processes, Generative Adversarial Networks, Diffusion Models, and Transformers.
... The Generative Adversarial Network (GAN), recently, has been applied in stock price prediction [29][30][31]. In their studies, the GAN model with Gated Recurrent Units (GRU) is used as a generator inputting the historical stock price and producing the future stock price. ...
Stock price prediction is a crucial task in the decision-making of investors. Forecasting successfully on future stock prices will help the investors to gain profit. However, it is difficult to predict exactly the trend of the stock market due to the complex relationship between stock prices and external factors such as news, global economy, public sentiments, and other sensitive financial information. Therefore, historical prices are the main investigation data for researchers since collecting external factors is still a challenge. Our motivation comes from the stock price’s varying trend and the relationship among stocks. To this end, we propose two approaches based on the long short-term memory (LSTM) model along with a deep concern in the historical data of stocks. (i) The input data of the LSTM model are enriched by integrating the historical price of stocks with their nearest neighbors in terms of similarity; (ii) a dynamic sliding window is applied in the prediction phase of the LSTM model based on the analysis of the significant change of the stock price. Experimental results on three stock datasets of the United States, Germany, and Vietnam show that our model outperforms the competitors in predicting the trend of stock price fluctuations. This paper is an extended version of our previous work at the IEEE International Conference on Big Data and Smart Computing (BigComp 2021).
Stock price movement prediction is an important task of the financial prediction field. The current mainstream approaches usually apply financial texts and some corresponding stock price information to predict the stock price movement. However, the current methods usually suffer from two shortcomings: 1) To reduce the stochasticity in the stock price and financial text information, some researchers adopt generative models to better treat the stochasticity while enduring the overfitting problem during training. 2) Although the current state-of-the-art methods based on the generative adversarial network have been proposed to reduce the overfitting, they only concentrate on the overfitting problem of the stock price information and neglect the above problem of financial text information with higher stochasticity. In this paper, we propose a self-regulated generative adversarial network by combining the generative adversarial network and cooperative network for the stock price movement prediction. Furthermore, the proposed model can effectively reduce the stochasticity and overfitting problems simultaneously for the stock price and the financial text information. The experimental results on the currently commonly used stock dataset based on tweets confirm that the proposed method can achieve the novelly state-of-the-art performance compared with some current advances.
Predicting the future price of financial assets has always been an important research topic in the field of quantitative finance. This paper attempts to use the latest artificial intelligence technologies to design and implement a framework for financial asset price prediction. The framework we use is divided into three modules: Feature Engineering, Regressor, and Hyper Optimizer. The Feature Engineering module extract multiple features using technical indicators, FinBERT, FFT, ARIMA, stacked auto-encoder, PCA and XGBoost. The Regressor module consists of a generative adversarial network, where the generator is Seq2Seq and the discriminator is GRU. The HyperOptimizer module will tune the parameter in GAN using the Bayesian optimization algorithm. Finally, we conducted numerical experiments on our framework, which shows that the framework implemented in this paper performs better than the benchmark method.
Deep learning has recently achieved great success in many areas due to its strong capacity in data process. For instance, it has been widely used in financial areas such as stock market prediction, portfolio optimization, financial information processing and trade execution strategies. Stock market prediction is one of the most popular and valuable area in finance. In this paper, we propose a novel architecture of Generative Adversarial Network (GAN) with the Multi-Layer Perceptron (MLP) as the discriminator and the Long Short-Term Memory (LSTM) as the generator for forecasting the closing price of stocks. The generator is built by LSTM to mine the data distributions of stocks from given data in stock market and generate data in the same distributions, whereas the discriminator designed by MLP aims to discriminate the real stock data and generated data. We choose the daily data on S&P 500 Index and several stocks in a wide range of trading days and try to predict the daily closing price. Experimental results show that our novel GAN can get a promising performance in the closing price prediction on the real data compared with other models in machine learning and deep learning.
Stock price prediction is an important issue in the financial world, as it contributes to the development of effective strategies for stock exchange transactions. In this paper, we propose a generic framework employing Long Short-Term Memory (LSTM) and convolutional neural network (CNN) for adversarial training to forecast high-frequency stock market. This model takes the publicly available index provided by trading software as input to avoid complex financial theory research and difficult technical analysis, which provides the convenience for the ordinary trader of nonfinancial specialty. Our study simulates the trading mode of the actual trader and uses the method of rolling partition training set and testing set to analyze the effect of the model update cycle on the prediction performance. Extensive experiments show that our proposed approach can effectively improve stock price direction prediction accuracy and reduce forecast error.
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic. Unlike most work on generative models, our primary goal is not to train a model that assigns high likelihood to test data, nor do we require the model to be able to learn well without using any labels. Using our new techniques, we achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN. The generated images are of high quality as confirmed by a visual Turing test: our model generates MNIST samples that humans cannot distinguish from real data, and CIFAR-10 samples that yield a human error rate of 21.3%. We also present ImageNet samples with unprecedented resolution and show that our methods enable the model to learn recognizable features of ImageNet classes.
In this paper we compare different types of recurrent units in recurrent
neural networks (RNNs). Especially, we focus on more sophisticated units that
implement a gating mechanism, such as a long short-term memory (LSTM) unit and
a recently proposed gated recurrent unit (GRU). We evaluate these recurrent
units on the tasks of polyphonic music modeling and speech signal modeling. Our
experiments revealed that these advanced recurrent units are indeed better than
more traditional recurrent units such as tanh units. Also, we found GRU to be
comparable to LSTM.
In this paper, we propose a novel neural network model called RNN Encoder--Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder--Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.
Stock market is a promising financial investment that can generate great wealth. However, the volatile nature of the stock market makes it a very high risk investment. Thus, a lot of researchers have contributed their efforts to forecast the stock market pricing and average movement. Researchers have used various methods in computer science and economics in their quests to gain a piece of this volatile information and make great fortune out of the stock market investment. This paper investigates various techniques for the stock market prediction using artificial neural network (ANN). The aim of this paper is to provide a review of the applications of ANN in stock market prediction in order to determine what can be done in the future.
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
Financial time-series modeling is a challenging problem as it retains various complex statistical properties and the mechanism behind the process is unrevealed to a large extent. In this paper, a deep neural networks based approach, generative adversarial networks (GANs) for financial time-series modeling is presented. GANs learn the properties of data and generate realistic data in a data-driven manner. The GAN model produces a time-series that recovers the statistical properties of financial time-series such as the linear unpredictability, the heavy-tailed price return distribution, volatility clustering, leverage effects, the coarse-fine volatility correlation, and the gain/loss asymmetry.
In 2016, more than the 80% of transactions in the Forex market (where the world’s currencies trade) have been directed by robots. The design of profitable automatic trading systems is becoming a challenging process. This requires a strong synergy of economists and computer scientists. Our aim is to provide an optimization framework for trading systems that starting from a generic strategy, enhances its performances by exploiting mathematical constraints. Moreover, the growth of new markets requires suitable solutions integrating computer science tools with economic analysis. In this work, we mainly refer to an emerging market known as Binary Options. Starting from basic strategies used every day in the stock markets by professional traders, we show how optimization issues enhance the outcoming performances. Tests on the optimized algorithms are conducted on both historical and real time data.
Generative adversarial networks (GANs) are one of the most popular methods for generating images today. While impressive results have been validated by visual inspection, a number of quantitative criteria have emerged only recently. We argue here that the existing ones are insufficient and need to be in adequation with the task at hand. In this paper we introduce two measures based on image classification—GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively. We evaluate a number of recent GAN approaches based on these two measures and demonstrate a clear difference in performance. Furthermore, we observe that the increasing difficulty of the dataset, from CIFAR10 over CIFAR100 to ImageNet, shows an inverse correlation with the quality of the GANs, as clearly evident from our measures.
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
Many statistical models, and in particular autoregressive-moving average time series models, can be regarded as means of transforming the data to white noise, that is, to an uncorrelated sequence of errors. If the parameters are known exactly, this random sequence can be computed directly from the observations; when this calculation is made with estimates substituted for the true parameter values, the resulting sequence is referred to as the "residuals," which can be regarded as estimates of the errors. If the appropriate model has been chosen, there will be zero autocorrelation in the errors. In checking adequacy of fit it is therefore logical to study the sample autocorrelation function of the residuals. For large samples the residuals from a correctly fitted model resemble very closely the true errors of the process; however, care is needed in interpreting the serial correlations of the residuals. It is shown here that the residual autocorrelations are to a close approximation representable as a singular linear transformation of the autocorrelations of the errors so that they possess a singular normal distribution. Failing to allow for this results in a tendency to overlook evidence of lack of fit. Tests of fit and diagnostic checks are devised which take these facts into account.
Generative Adversarial Nets [8] were recently introduced as a novel way to
train generative models. In this work we introduce the conditional version of
generative adversarial nets, which can be constructed by simply feeding the
data, y, we wish to condition on to both the generator and discriminator. We
show that this model can generate MNIST digits conditioned on class labels. We
also illustrate how this model could be used to learn a multi-modal model, and
provide preliminary examples of an application to image tagging in which we
demonstrate how this approach can generate descriptive tags which are not part
of training labels.
Autoregressive integrated moving average (ARIMA) is one of the popular linear models in time series forecasting during the past three decades. Recent research activities in forecasting with artificial neural networks (ANNs) suggest that ANNs can be a promising alternative to the traditional linear methods. ARIMA models and ANNs are often compared with mixed conclusions in terms of the superiority in forecasting performance. In this paper, a hybrid methodology that combines both ARIMA and ANN models is proposed to take advantage of the unique strength of ARIMA and ANN models in linear and nonlinear modeling. Experimental results with real data sets indicate that the combined model can be an effective way to improve forecasting accuracy achieved by either of the models used separately.
Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves; the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands; indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context-dependent, while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction.
A discussion is presented of a buying- and selling-time prediction
system for stocks on the Tokyo Stock Exchange and the analysis of
internal representation. The system is based on modular neural networks.
The authors developed a number of learning algorithms and prediction
methods for the TOPIX (Tokyo Stock Exchange Prices Indexes) prediction
system. The prediction system achieved accurate predictions, and the
simulation on stocks trading showed an excellent profit
Deep learning for event-driven stock prediction
- X Ding
- Y Zhang
- T Liu
- J Duan
Automatic differentiation in pytorch
- A Paszke
- S Gross
- S Chintala
- G Chanan
- E Yang
- Z De Vito
Generative Adversarial Network for Stock Market price Prediction
- Ricardo Alberto
- Carrillo Romero
Generative adversarial nets
- I Goodfellow
- J Pouget-Abadie
- Mirza Jean
- Xu Mehdi
- Warde-Farley Bing
- Ozair David
Pytorch: An imperative style, high-performance deep learning library
- A Paszke
- S Gross
- F Massa
- A Lerer
- J Bradbury
- G Chanan
Pytorch: An imperative style, high-performance deep learning library
- paszke
Deep learning for event-driven stock prediction
- ding