Robust Analysis of Stock Price Time Series Using CNN and LSTM-Based Deep Learning Models
Praxis Business School（普拉克西斯商学院）
Sidra Mehtab, Jaydip Sen, Subhasis Dasgupta
备注：
The paper is the accepted version of our work in the 4th IEEE International Conference on Electronics, Communication, and Aerospace Technology (ICECA'20), November 5 - 7, 2020, Coimbatore, INDIA, The paper consists of 10 pages. It contains 12 figures and 8 tables
Prediction of stock price and stock price movement patterns has always been a critical area of research. While the well-known efficient market hypothesis rules out any possibility of accurate prediction of stock prices, there are formal propositions in the literature demonstrating accurate modeling of the predictive systems that can enable us to predict stock prices with a very high level of accuracy. In this paper, we present a suite of deep learning-based regression models that yields a very high level of accuracy in stock price prediction. To build our predictive models, we use the historical stock price data of a well-known company listed in the National Stock Exchange (NSE) of India during the period December 31, 2012 to January 9, 2015. The stock prices are recorded at five minutes intervals of time during each working day in a week. Using these extremely granular stock price data, we build four convolutional neural network (CNN) and five long- and short-term memory (LSTM)-based deep learning models for accurate forecasting of the future stock prices. We provide detailed results on the forecasting accuracies of all our proposed models based on their execution time and their root mean square error (RMSE) values.
SRM Institute of Science and Technology（SRM科学技术研究所）
Economy is severely dependent on the stock market. An uptrend usually corresponds to prosperity while a downtrend correlates to recession. Predicting the stock market has thus been a centre of research and experiment for a long time. Being able to predict short term movements in the market enables investors to reap greater returns on their investments. Stock prices are extremely volatile and sensitive to financial market. In this paper we use Deep Learning networks to predict stock prices, assimilating financial, business and technology news articles which present information about the market.…
Stock price prediction can be made more efficient by considering the price fluctuations and understanding the sentiments of people. A limited number of models understand financial jargon or have labelled datasets concerning stock price change. To overcome this challenge, we introduced FinALBERT, an ALBERT based model trained to handle financial domain text classification tasks by labelling Stocktwits text data based on stock price change. We collected Stocktwits data for over ten years for 25 different companies, including the major five FAANG (Facebook, Amazon, Apple, Netflix, Google). These …
Designing robust systems for precise prediction of future prices of stocks has always been considered a very challenging research problem. Even more challenging is to build a system for constructing an optimum portfolio of stocks based on the forecasted future stock prices. We present a deep learning-based regression model built on a long-and-short-term memory network (LSTM) network that automatically scraps the web and extracts historical stock prices based on a stock's ticker name for a specified pair of start and end dates, and forecasts the future stock prices. We deploy the model on 75 si…
The importance of considering the volumes to analyze stock prices movements can be considered as a well-accepted practice in the financial area. However, when we look at the scientific production in this field, we still cannot find a unified model that includes volume and price variations for stock assessment purposes. In this paper we present a computer model that could fulfill this gap, proposing a new index to evaluate stock prices based on their historical prices and volumes traded. Besides the model can be considered mathematically very simple, it was able to improve significantly the per…
Nankai University（南开大学）；Shenzhen Research Institute, Nankai University（南开大学深圳研究院）；Orient Securities Co. Ltd（东方证券股份有限公司）；Guangxi Academy of Social Science（广西社会科学院）
Stock market plays an important role in the economic development. Due to the complex volatility of the stock market, the research and prediction on the change of the stock price, can avoid the risk for the investors. The traditional time series model ARIMA can not describe the nonlinearity, and can not achieve satisfactory results in the stock prediction. As neural networks are with strong nonlinear generalization ability, this paper proposes an attention-based CNN-LSTM and XGBoost hybrid model to predict the stock price. The model constructed in this paper integrates the time series model, th…
Prediction of future movement of stock prices has been a subject matter of many research work. There is a gamut of literature of technical analysis of stock prices where the objective is to identify patterns in stock price movements and derive profit from it. Improving the prediction accuracy remains the single most challenge in this area of research. We propose a hybrid approach for stock price movement prediction using machine learning, deep learning, and natural language processing. We select the NIFTY 50 index values of the National Stock Exchange of India, and collect its daily price move…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Department of Electrical & Computer Engineering（电气与计算机工程系）
In this work, we apply machine learning techniques to historical stock prices to forecast future prices. To achieve this, we use recursive approaches that are appropriate for handling time series data. In particular, we apply a linear Kalman filter and different varieties of long short-term memory (LSTM) architectures to historical stock prices over a 10-year range (1/1/2011 - 1/1/2021). We quantify the results of these models by computing the error of the predicted values versus the historical values of each stock. We find that of the algorithms we investigated, a simple linear Kalman filter …
Praxis Business School（实践商学院）；NSHM Knowledge Campus（NSHM知识园区）
Building predictive models for robust and accurate prediction of stock prices and stock price movement is a challenging research problem to solve. The well-known efficient market hypothesis believes in the impossibility of accurate prediction of future stock prices in an efficient stock market as the stock prices are assumed to be purely stochastic. However, numerous works proposed by researchers have demonstrated that it is possible to predict future stock prices with a high level of precision using sophisticated algorithms, model architectures, and the selection of appropriate variables in t…
News-Driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced Deep Learning Models
Pegasystems India Worldwide Pvt Ltd（佩加系统印度私人有限公司）；Vardhaman College of Engineering（瓦尔达曼工程学院）；Vasavi College of Engineering（瓦萨维工程学院）；D. K. College（D.K.学院）
The stock market is volatile and complicated, especially in 2020. Because of a series of global and regional "black swans," such as the COVID-19 pandemic, the U.S. stock market triggered the circuit breaker three times within one week of March 9 to 16, which is unprecedented throughout history. Affected by the whole circumstance, the stock prices of individual corporations also plummeted by rates that were never predicted by any pre-developed forecasting models. It reveals that there was a lack of satisfactory models that could predict the changes in stocks prices when catastrophic, highly unl…
Prediction of stock prices has been an important area of research for a long time. While supporters of the efficient market hypothesis believe that it is impossible to predict stock prices accurately, there are formal propositions demonstrating that accurate modeling and designing of appropriate variables may lead to models using which stock prices and stock price movement patterns can be very accurately predicted. In this work, we propose an approach of hybrid modeling for stock price prediction building different machine learning and deep learning-based models. For the purpose of our study, …
The evaluation of the financial markets to predict their behaviour have been attempted using a number of approaches, to make smart and profitable investment decisions. Owing to the highly non-linear trends and inter-dependencies, it is often difficult to develop a statistical approach that elucidates the market behaviour entirely. To this end, we present a long-short term memory (LSTM) based model that leverages the sequential structure of the time-series data to provide an accurate market forecast. We then develop a decision making StockBot that buys/sells stocks at the end of the day with th…
Neural networks for stock price prediction(NNSPP) have been popular for decades. However, most of its study results remain in the research paper and cannot truly play a role in the securities market. One of the main reasons leading to this situation is that the prediction error(PE) based evaluation results have statistical flaws. Its prediction results cannot represent the most critical financial direction attributes. So it cannot provide investors with convincing, interpretable, and consistent model performance evaluation results for practical applications in the securities market. To illustr…
Columbia University（哥伦比亚大学）；Beijing Institute of Technology（北京理工大学）
Stock price prediction is important for value investments in the stock market. In particular, short-term prediction that exploits financial news articles is promising in recent years. In this paper, we propose a novel deep neural network DP-LSTM for stock price prediction, which incorporates the news articles as hidden information and integrates difference news sources through the differential privacy mechanism. First, based on the autoregressive moving average model (ARMA), a sentiment-ARMA is formulated by taking into consideration the information of financial news articles in the model. The…
We employ both random forests and LSTM networks (more precisely CuDNNLSTM) as training methodologies to analyze their effectiveness in forecasting out-of-sample directional movements of constituent stocks of the S&P 500 from January 1993 till December 2018 for intraday trading. We introduce a multi-feature setting consisting not only of the returns with respect to the closing prices, but also with respect to the opening prices and intraday returns. As trading strategy, we use Krauss et al. (2017) and Fischer & Krauss (2018) as benchmark. On each trading day, we buy the 10 stocks with the highe…
Columbia University（哥伦比亚大学）；Beijing Institute of Technology（北京理工大学）；New York University Shanghai（上海纽约大学）
Midterm stock price prediction is crucial for value investments in the stock market. However, most deep learning models are essentially short-term and applying them to midterm predictions encounters large cumulative errors because they cannot avoid anomalies. In this paper, we propose a novel deep neural network Mid-LSTM for midterm stock prediction, which incorporates the market trend as hidden states. First, based on the autoregressive moving average model (ARMA), a midterm ARMA is formulated by taking into consideration both hidden states and the capital asset pricing model. Then, a midterm…
This paper tends to define the quantitative relationship between the stock price and time as a time function. Based on the empirical evidence that the log-return of a stock is the series of white noise, a mathematical model of the integral white noise is established to describe the phenomenon of stock price movement. A deductive approach is used to derive the auto-correlation function, displacement formula and power spectral density of the stock price movement, which reveals not only the characteristics and rules of the movement but also the predictability of the stock price. The deductive fun…
School of Industrial Management Engineering, Korea University（高丽大学产业管理工程学院）；Harbin Institute of Technology（哈尔滨工业大学）
The prediction of a stock market direction may serve as an early recommendation system for short-term investors and as an early financial distress warning system for long-term shareholders. Many stock prediction studies focus on using macroeconomic indicators, such as CPI and GDP, to train the prediction model. However, daily data of the macroeconomic indicators are almost impossible to obtain. Thus, those methods are difficult to be employed in practice. In this paper, we propose a method that directly uses prices data to predict market index direction and stock price direction. An extensive …
Designing robust and accurate prediction models has been a viable research area since a long time. While proponents of a well-functioning market predictors believe that it is difficult to accurately predict market prices but many scholars disagree. Robust and accurate prediction systems will not only be helpful to the businesses but also to the individuals in making their financial investments. This paper presents an LSTM model with two different input approaches for predicting the short-term stock prices of two Indian companies, Reliance Industries and Infosys Ltd. Ten years of historic data …
This paper examines the short-run relationships between oil prices and GCC stock markets. Since GCC countries are major world energy market players, their stock markets may be susceptible to oil price shocks. To account for the fact that stock markets may respond nonlinearly to oil price shocks, we have examined both linear and nonlinear relationships. Our findings show that there are significant links between the two variables in Qatar, Oman, and UAE. Thus, stock markets in these countries react positively to oil price increases. For Bahrain, Kuwait, and Saudi Arabia we found that oil price c…
We propose procedures for testing whether stock price processes are martingales based on limit order type betting strategies. We first show that the null hypothesis of martingale property of a stock price process can be tested based on the capital process of a betting strategy. In particular with high frequency Markov type strategies we find that martingale null hypotheses are rejected for many stock price processes.
While the use of volatilities is pervasive throughout finance, our ability to determine the instantaneous volatility of stocks is nascent. Here, we present a method for measuring the temporal behavior of stocks, and show that stock prices for 24 DJIA stocks follow a stochastic process that describes an efficiently priced stock while using a volatility that changes deterministically with time. We find that the often observed, abnormally large kurtoses are due to temporal variations in the volatility. Our method can resolve changes in volatility and drift of the stocks as fast as a single day us…
MAE, MSE and RMSE performance indicators are used to analyze the performance of different stocks predicted by LSTM and ARIMA models in this paper. 50 listed company stocks from finance.yahoo.com are selected as the research object in the experiments. The dataset used in this work consists of the highest price on transaction days, corresponding to the period from 01 January 2010 to 31 December 2018. For LSTM model, the data from 01 January 2010 to 31 December 2015 are selected as the training set, the data from 01 January 2016 to 31 December 2017 as the validation set and the data from 01 Janua…
Boosting Stock Price Prediction with Anticipated Macro Policy Changes
Institute of Electrical and Electronics Engineers（电气与电子工程师协会）；University of Tennessee, Chattanooga（田纳西大学查塔努加分校）；University of South Dakota（南达科他大学）；University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）
We analyze the interaction between stock prices of big companies in the USA and Germany using Granger Causality. We claim that the increase in pair-wise Granger causality interaction between prices in the times of crisis is the consequence of simultaneous response of the markets to the outside events or external stimulus that is considered as a common driver to all the stocks, not a result of real causal predictability between the prices themselves. An alternative approach through recurrence analysis in single stock price series supports this claim. The observed patterns in the price of stocks…
This paper investigates the effect of cross-shareholding on stock price synchronicity, as a measure of price informativeness, of the listed firms in the Chinese stock market. We gauge firms' levels of cross-shareholdings in terms of centrality in the cross-shareholding network. It is confirmed that it is through a noise-reducing process that cross-shareholding promotes price synchronicity and reduces price delay. More importantly, this effect on price informativeness is pronounced for large firms and in the periods of market downturns. Overall, our analyses provide insights into the relation b…
Rice University（莱斯大学）；Department of Economics（经济学系）
In this work we use Recurrent Neural Networks and Multilayer Perceptrons to predict NYSE, NASDAQ and AMEX stock prices from historical data. We experiment with different architectures and compare data normalization techniques. Then, we leverage those findings to question the efficient-market hypothesis through a formal statistical test.
Recent academic work has developed a method to determine, in real time, if a given stock is exhibiting a price bubble. Currently there is speculation in the financial press concerning the existence of a price bubble in the aftermath of the recent IPO of LinkedIn. We analyze stock price tick data from the short lifetime of this stock through May 24, 2011, and we find that LinkedIn has a price bubble.
Stock exchanges are considered major players in financial sectors of many countries. Most Stockbrokers, who execute stock trade, use technical, fundamental or time series analysis in trying to predict stock prices, so as to advise clients. However, these strategies do not usually guarantee good returns because they guide on trends and not the most likely price. It is therefore necessary to explore improved methods of prediction. The research proposes the use of Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation and develops a model of configuration …
Price limit trading rules are adopted in some stock markets (especially emerging markets) trying to cool off traders' short-term trading mania on individual stocks and increase market efficiency. Under such a microstructure, stocks may hit their up-limits and down-limits from time to time. However, the behaviors of price limit hits are not well studied partially due to the fact that main stock markets such as the US markets and most European markets do not set price limits. Here, we perform detailed analyses of the high-frequency data of all A-share common stocks traded on the Shanghai Stock E…
The prediction of stock prices is an important task in economics, investment and making financial decisions. This has, for decades, spurred the interest of many researchers to make focused contributions to the design of accurate stock price predictive models; of which some have been utilized to predict the next day opening and closing prices of the stock indices. This paper proposes the design and implementation of a hybrid symbiotic organisms search trained feedforward neural network model for effective and accurate stock price prediction. The symbiotic organisms search algorithm is used as a…
Designing robust frameworks for precise prediction of future prices of stocks has always been considered a very challenging research problem. The advocates of the classical efficient market hypothesis affirm that it is impossible to accurately predict the future prices in an efficiently operating market due to the stochastic nature of the stock price variables. However, numerous propositions exist in the literature with varying degrees of sophistication and complexity that illustrate how algorithms and models can be designed for making efficient, accurate, and robust predictions of stock price…
This paper analyzes the quantitative relations between stock prices and quantities of tradable stock shares in Chinese stock markets at six time points by means of Exploratory Data Analysis (EDA) method. It is found the resulting formulae have the same structure but different parameters. This paper also uses these relationships in order to analyse the feasibility of policies for Chinese Government to sell the state-owned shares in Chinese stock markets.
Many studies assume stock prices follow a random process known as geometric Brownian motion. Although approximately correct, this model fails to explain the frequent occurrence of extreme price movements, such as stock market crashes. Using a large collection of data from three different stock markets, we present evidence that a modification to the random model -- adding a slow, but significant, fluctuation to the standard deviation of the process -- accurately explains the probability of different-sized price changes, including the relative high frequency of extreme movements. Furthermore, we…
Stock prices are driven by various factors. In particular, many individual investors who have relatively little financial knowledge rely heavily on the information from news stories when making investment decisions in the stock market. However, these stories may not reflect future stock prices because of the subjectivity in the news; stock prices may instead affect the news contents. This study aims to discover whether it is news or stock prices that have a greater impact on the other. To achieve this, we analyze the relationship between news sentiment and stock prices based on time series ana…
Earnings calls are hosted by management of public companies to discuss the company's financial performance with analysts and investors. Information disclosed during an earnings call is an essential source of data for analysts and investors to make investment decisions. Thus, we leverage earnings call transcripts to predict future stock price dynamics. We propose to model the language in transcripts using a deep learning framework, where an attention mechanism is applied to encode the text data into vectors for the discriminative network classifier to predict stock price movements. Our empirica…
Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion
Graduate Institute of Electrical Engineering, National Taiwan University（国立台湾大学电子工程研究所）；Institute of Information Science, Academia Sinica（学术院信息科学研究所）；United Link Co., Ltd.（联合链接公司）；University of Washington（华盛顿大学）；National Tsing Hua University（国立清华大学）
We analyze daily prices of 29 commodities and 2449 stocks, each over a period of $\approx 15$ years. We find that the price fluctuations for commodities have a significantly broader multifractal spectrum than for stocks. We also propose that multifractal properties of both stocks and commodities can be attributed mainly to the broad probability distribution of price fluctuations and secondarily to their temporal organization. Furthermore, we propose that, for commodities, stronger higher order correlations in price fluctuations result in broader multifractal spectra.
We study the rank distribution, the cumulative probability, and the probability density of returns of stock prices of listed firms traded in four stock markets. We find that the rank distribution and the cumulative probability of stock prices traded in are consistent approximately with the Zipf's law or a power law. It is also obtained that the probability density of normalized returns for listed stocks almost has the form of the exponential function. Our results are compared with those of other numerical calculations.
