Stock Price Model Research Articles

Option Pricing Based on Neural Stochastic Differential Equations

Firstly, based on the Black-Scholes stock price model, the neural stochastic differential equation (NSDE) model was established by parameterizing the asset return rate and volatility as a drift network and a diffusion network, respectively. Secondly, in the empirical analysis, the underlying asset as a single stock option was used as the research object, and real stock data was used for the network training and testing. The experimental results show that the NSDE model can overcome the defects of the constant assumption of the Black-Scholes model. Finally, for the case where the price of the underlying asset of the option was unobservable, we proposed that the price of any target option and the price of a known option could be constrained within the Wasserstein distance of their risk-neutral equivalent martingale measure, and theoretically proved the method.

Application of the Fractal Brownian Motion to the Athens Stock Exchange

The Athens Stock Exchange (ASE) is a dynamic financial market with complex interactions and inherent volatility. Traditional models often fall short in capturing the intricate dependencies and long memory effects observed in real-world financial data. In this study, we explore the application of fractional Brownian motion (fBm) to model stock price dynamics within the ASE, specifically utilizing the Athens General Composite (ATG) index. The ATG is considered a key barometer of the overall health of the Greek stock market. Investors and analysts monitor the index to gauge investor sentiment, economic trends, and potential investment opportunities in Greek companies. We find that the Hurst exponent falls outside the range typically associated with fractal Brownian motion. This, combined with the established non-normality of increments, disfavors both geometric Brownian motion and fractal Brownian motion models for the ATG index.

Application of Stochastic Processes in Financial Market Models

This paper explores the significant role of stochastic processes in financial modeling, tracing the evolution from basic Brownian motion to sophisticated stochastic differential equations used in modern financial markets. Beginning with the historical development of Brownian motion, identified by Robert Brown and later mathematically modeled by Louis Bachelier for stock price fluctuations, the paper outlines its foundational influence on the Efficient Market Hypothesis and the random walk theory. The extension of these concepts in the Black-Scholes model for option pricing highlights the practical applications of these theories in predicting financial outcomes. The discussion progresses to geometric Brownian motion (GBM) and its crucial role in stock price modeling, emphasizing its use in Monte Carlo simulations for option pricing. The limitations of the Black-Scholes model and GBM in dealing with real market conditions such as stochastic volatility and jump-diffusion processes are addressed, showcasing the evolution of more complex models like the Heston model and GARCH. Interest rate models like the Vasicek and Cox-Ingersoll-Ross models are evaluated for their real-world applicability, particularly in scenarios of low and negative interest rates. This comprehensive review not only underscores the theoretical advancements in financial modeling but also its practical implications in contemporary financial markets.

Explainable deep learning model for stock price forecasting using textual analysis

Stock price forecasting is a challenging task because financial time series are primarily nonlinear, noisy, and disordered systems that are complicated to forecast. Deep learning models show promise in this domain along with natural language processing, to extract relevant features from text data and map them to numerical representations. This study aims to forecast stock prices using text analysis and deep learning approaches and explain the models using explainable AI. We construct a World Halal Tourism Composite Sentiment Index (WHTCSI) using text analysis to forecast halal tourism stock price. The results suggest that Convolutional Neural Networks (CNN) outperform all other models. The results are robust when considering country-level data. In addition, model explanations show that the index contributes 35.55% to the forecasting model, indicating irrational investment activity and herding behavior in the halal tourism industry. The study’s findings have significant implications for investors, analysts, and portfolio managers in making investment decisions.

Stock Closing Price Prediction Based on the ARIMA-GARCH Model

Amidst a burgeoning stock market, a plethora of predictive models for stock prices have been steadily surfacing, with a wide array of Autoregressive models finding extensive application. This study sets out to evaluate the efficacy of the ARIMA-GARCH model in the domain of stock price prediction, taking as its dataset the stock information of Jinan Hi-Tech Development (600807). This paper begins by transforming the closing prices of Jinan Hi-Tech Development (600807) from July 13, 2023, to July 27, 2023, into a time series for the purpose of model fitting, identifying the ARIMA model parameters, and examining ARCH effects alongside the normality and independence of residuals. Subsequently, GARCH model parameters are discerned and integrated with the ARIMA model to establish the ARIMA-GARCH model, which is then subjected to residual testing. Concluding the study, a comparative error analysis between the predicted and actual closing prices reveals that the ARIMA-GARCH model boasts substantial accuracy in short-term stock price forecasting.

A Case Study of Society General Securities based on ARIMA Model

Stock price changes have always been a high concern for investors. Stock price modeling can indicate the stock changing trend, which can not only provide references for investors, but also can see the future development of the relevant market by analyzing the changing stock prices. Therefore, this paper establishes an Auto-Regressive Moving Average Model (ARIMA) of the opening price as well as the closing price of the trading day in Industrial Securities Co., Ltd. from November 2021 to August 2023 to predict the opening and closing price of the next seven periods of direction. The results show that the opening price will have a small fluctuation in the next 7 periods and the closing price will decline slowly. The goodness of fit of opening and closing prices are greater than 0.98, so this result is good. The result shows that this prediction of stock price by the ARIMA model is feasible and the result can be used as a basis for investors to predict future stock prices.

Quantum Uncertainty and the Black-Scholes Formula

The publication of the Black-Scholes formula in 1973 appeared for the first time to put the pricing of financial options onto a rational and objective basis. Its adoption transformed the perception of option pricing from a form of gambling to scientific risk management, and led to a huge increase in options trading. However while the formula revolutionised the world of finance, and remains the industry-standard pricing model today, its proof relies on a number of assumptions about price behaviour which are often contested, such as that log prices follow a random walk with constant volatility, and that one can constantly buy or sell stocks and options without incurring transaction fees. This paper presents an alternative approach to option pricing, based on a quantum oscillator model of stock prices. In the quantum model, the bid/ask spread between buy and sell prices is treated as a fundamental measure of uncertainty, and volatility is not constant but exhibits a smile-like dependence on strike. We show how the Black-Scholes model and its assumptions lead to a systematic mispricing of commonly-traded options, while results can be improved by adopting the quantum model.

Shanghai Stock Composite Index Forecasts: Evidence from ARIMA and LSTM

Prediction of stock prices is a classic problem. People are always trying to predict stock prices as accurately as possible, and also trying to build stock price model. With the development of technology, machine learning has been applied more and more to stock prediction problems, and good results have been obtained. This paper selects the Shanghai Stock Composite Index from 1990 to 2016 and forecasts its closing price. First, the ARIMA (1,1,1) model is established for the closing price sequence after first-order difference, and then the two-layer LSTM model is constructed to visualize the prediction results of the two models and calculate rmse respectively. Comparing the prediction results of the two models, it is concluded that LSTM has better prediction effect on the data set used in this paper. This paper find that ARIMA has some cons that it is Not built for long-term forecasting and parameters are subjective. It does not predict as well as LSTM when there is a turning point.

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Calculation Option Price on Shares PT. Nippon Indosari Corpindo Tbk. with Fuzzy Binomial Tree Model

The Cox-Ross-Rubinstein binomial tree model is widely used in stock and derivative securities calculations, such as options calculations. The binomial CRR model assumes that the parameter increases in option prices and decreases in option prices so this model produces stock price movements up and down stock price movement. However, stock price movements show price fluctuations and cause the volatility of the value to be unsuitable. In this study, modeling stock and option price movements using a fuzzy binomial tree model. The data used was data on the movement of the stock price of Nippon Indosari Corpindo Ltd Plc from February 2021 to January 2022. The results showed that for February 2022, with a risk size of 90%, the selling price options with the greatest volatility of 51.6484081, medium volatility of 33.33154354, and the smallest volatility of 28.17155892.

Research on the Tencent Company Stock Price Based on ARIMA Model

This paper presents a comprehensive analysis of Tencent Holdings Limited's stock performance over the past five years. This paper explores the multifaceted factors influencing stock price volatility, including economic indicators, regulatory changes, industry developments, and technological innovations. Employing an ARIMA (0,1,0) model, this paper assesses the time series data of Tencent's stock price and scrutinize model adequacy through various statistical tests. Results suggest that the constant term in the ARIMA model may not be statistically significant, which emphasizing the need for a nuanced approach to stock price modeling. Predictive values for a 12-phase forecast reveal a declining trend in Tencent's stock price. The root-mean-square deviation (RMSD) is computed to gauge prediction accuracy. Additionally, the residual Lagrange multiplier correlation finds no significant correlation between residuals and independent variables. This analysis underscores the complexity of stock price determination and advocates for a holistic approach, consider both numerical analysis and qualitative factors. Investors are advised to maintain a long-term perspective when evaluating Tencent's market potential.

Research on momentum strategy and contrarian strategy in AI stock prediction

The emergence of ChatGPT has significantly enhanced the recognition and acceptance of artificial intelligence concept stocks within the Chinese stock market. Nevertheless, the short- and long-term fluctuations in the prices of AI companies remain uncertain. Therefore, the purpose of this research is to determine optimal strategy for evaluating the suitability of the contrarian strategy versus the momentum strategy in predicting the stock prices of AI concept stocks in the Chinese stock market. Based on a cross-comparison of the Chinese financial data sources iFinD and Wind Economic Database (EDB), this study collects the price data of AI concept stocks over the past six months, starting from the date of ChatGPT's publication. This study employ Python to model stock price movements for both the momentum and reversal strategies. The goodness of fit is evaluated by comparing the modeled stock prices with the actual stock prices. This study demonstrates that the momentum strategy exhibits greater explanatory power than the contrarian strategy, accurately predicting 84.21% of artificial intelligence concept stocks. However, other studies suggest that while AI concept stocks continue to rise, momentum strategies remain effective, whereas when market sentiment cools down, contrarian strategies become more suitable for Chinese AI concept stocks. Hence, in China, the effectiveness of these strategies may vary depending on the prevailing market conditions.

A novel hybrid model for stock price forecasting integrating Encoder Forest and Informer

A novel hybrid model for stock price forecasting integrating Encoder Forest and Informer

ResNLS: An improved model for stock price forecasting

AbstractStock prices forecasting has always been a challenging task. Although many research projects adopt machine learning and deep learning algorithms to address the problem, few of them pay attention to the varying degrees of dependencies between stock prices. In this paper we introduce a hybrid model that improves stock price prediction by emphasizing the dependencies between adjacent stock prices. The proposed model, ResNLS, is mainly composed of two neural architectures, ResNet and LSTM. ResNet serves as a feature extractor to identify dependencies between stock prices across time windows, while LSTM analyses the initial time‐series data with the combination of dependencies which considered as residuals. In predicting the SSE Composite Index, our experiment reveals that when the closing price data for the previous five consecutive trading days is used as the input, the performance of the model (ResNLS‐5) is optimal compared to those with other inputs. Furthermore, ResNLS‐5 outperforms vanilla CNN, RNN, LSTM, and BiLSTM models in terms of prediction accuracy. It also demonstrates at least a 20% improvement over the current state‐of‐the‐art baselines. To verify whether ResNLS‐5 can help clients effectively avoid risks and earn profits in the stock market, we construct a quantitative trading framework for back testing. The experimental results show that the trading strategy based on predictions from ResNLS‐5 can successfully mitigate losses during declining stock prices and generate profits in the periods of rising stock prices.

Stock Price Prediction Using Machine Learning

Abstract—As the need for precise and fast stock price projections is growing as financial markets continue to become more complicated. The use of Long Short-Term Memory (LSTM) neural networks for stock price forecasting is investigated in this paper. LSTMs are especially important for time series prediction tasks because they are good at capturing temporal dependencies in sequential data. In this study, LSTM models are trained and evaluated using historical stock price data while taking into account a variety of input features and hyperparameters. By contrasting the performance of LSTM models with conventional machine learning techniques, the advantages and disadvantages of each methodology are brought to light. The findings showed that LSTM models offer greater predictive capabilities, highlighting its potential in improving investment decisions and furthermore, the analysis of IBM Company Stock Price Values and model performance configurations add to the expanding body of knowledge about using deep learning approaches for financial forecasting. Keywords—Machine Learning, Neural Networks, RNN, Linear Regression, LSTM, Supervised Learning.

Stock Price Model in Manufacturing Companies

This study aims to analyse and answer the phenomenon of Stock Price (SP) with its determinants; Return On Assets (ROA), Dividend Pay-Out Ratio (DPR), Firm Size (SIZE) and Leverage (DER). The model of this study formula is a theoretical framework to find out the factors that influence SP through DER. First model results; ROA has a significant effect on DER. The same results also apply to SIZE, while DPR has no significant effect on DER. The results of the second model; ROA has a significant effect on SP. The same results also apply to SIZE, but they are negatively correlated. The results are different for DER and DPR, both of which have no significant effect on SP so that DER as an intervening variable does not function to mediate SP. The most dominant or sensitive variable in the two research models occurs in ROA. This research can be used as a guide for capital market players in Indonesia to detect what will happen to SP if the variables in this research experience movement. The value of this research is that the SP model formulation via DER is not appropriate for the manufacturing sector.

A Deep Learning Approach with Extensive Sentiment Analysis for Quantitative Investment

Recently, deep-learning-based quantitative investment is playing an increasingly important role in the field of finance. However, due to the complexity of the stock market, establishing effective quantitative investment methods is facing challenges from various aspects because of the complexity of the stock market. Existing research has inadequately utilized stock news information, overlooking significant details within news content. By constructing a deep hybrid model for comprehensive analysis of historical trading data and news information, complemented by momentum trading strategies, this paper introduces a novel quantitative investment approach. For the first time, we fully consider two dimensions of news, including headlines and contents, and further explore their combined impact on modeling stock price. Our approach initially employs fundamental analysis to screen valuable stocks. Subsequently, we built technical factors based on historical trading data. We then integrated news headlines and content summarized through language models to extract semantic information and representations. Lastly, we constructed a deep neural model to capture global features by combining technical factors with semantic representations, enabling stock prediction and trading decisions. Empirical results conducted on over 4000 stocks from the Chinese stock market demonstrated that incorporating news content enriched semantic information and enhanced objectivity in sentiment analysis. Our proposed method achieved an annualized return rate of 32.06% with a maximum drawdown rate of 5.14%. It significantly outperformed the CSI 300 index, indicating its applicability to guiding investors in making more effective investment strategies and realizing considerable returns.

Determining The Optimal Portfolio Markowitz Model on Moving Stock Prices Using Brown Motion Geometry

Stock price movements that fluctuate and follow a stochastic process will make it difficult for investors to start investing. For that, we need a stochastic mathematical model. The Brownian geometry motion model is one of the stochastic models that can be used to display the condition of a stock's price movement. Investment is related to the rate of return (return) and the risk obtained. The higher the rate of return obtained, the higher the risk obtained. Therefore, a portfolio calculation is needed, one of which is using the Markowitz model. The Markowitz model can be used to determine the optimal portfolio. The purpose of this study is to model stock prices and form an optimal portfolio. The stock price data used are BBRI, TLKM, and ADRO for the period from 1 July 2021 to 31 August 2022. The results obtained from this study are that there are three portfolio preferences. If investors like high risk to get high returns, then the combined allocation of funds for BBRI, TLKM and ADRO shares is 10.51%, 42.05% and 47.44% respectively. If investors do not like high risk but still want to get a return that is balanced with risk, then the combination of fund allocation for shares of BBRI, TLKM and ADRO is 22.62%, 46.63% and 30.75%, respectively. If the investor chooses minimum risk, the combined allocation of BBRI, TLKM and ADRO shares is 34.73%, 51.21% and 14.06%, respectively.

Predicting extreme events in the stock market using generative adversarial networks

Accurately predicting extreme stock market fluctuations at the right time will allow traders and investors to make better-informed investment decisions and practice more efficient financial risk management. However, extreme stock market events are particularly hard to model because of their scarce and erratic nature. Moreover, strong trading strategies, market stress tests, and portfolio optimization largely rely on sound data. While the application of generative adversarial networks (GANs) for stock forecasting has been an active area of research, there is still a gap in the literature on using GANs for extreme market movement prediction and simulation. In this study, we proposed a framework based on GANs to efficiently model stock prices’ extreme movements. By creating synthetic real-looking data, the framework simulated multiple possible market-evolution scenarios, which can be used to improve the forecasting quality of future market variations. The fidelity and predictive power of the generated data were tested by quantitative and qualitative metrics. Our experimental results on S&P 500 and five emerging market stock data show that the proposed framework is capable of producing a realistic time series by recovering important properties from real data. The results presented in this work suggest that the underlying dynamics of extreme stock market variations can be captured efficiently by some state-of-the-art GAN architectures. This conclusion has great practical implications for investors, traders, and corporations willing to anticipate the future trends of their financial assets. The proposed framework can be used as a simulation tool to mimic stock market behaviors.