Future Prices Research Articles

Forecasting relative returns for S&P 500 stocks using machine learning

Forecasting changes in stock prices is extremely challenging given that numerous factors cause these prices to fluctuate. The random walk hypothesis and efficient market hypothesis essentially state that it is not possible to systematically, reliably predict future stock prices or forecast changes in the stock market overall. Nonetheless, machine learning (ML) techniques that use historical data have been applied to make such predictions. Previous studies focused on a small number of stocks and claimed success with limited statistical confidence. In this study, we construct feature vectors composed of multiple previous relative returns and apply the random forest (RF), support vector machine (SVM), and long short-term memory (LSTM) ML methods as classifiers to predict whether a stock can return 2% more than its index in the following 10 days. We apply this approach to all S&P 500 companies for the period 2017–2022. We assess performance using accuracy, precision, and recall and compare our results with a random choice strategy. We observe that the LSTM classifier outperforms RF and SVM, and the data-driven ML methods outperform the random choice classifier (p = 8.46e−17 for accuracy of LSTM). Thus, we demonstrate that the probability that the random walk and efficient market hypotheses hold in the considered context is negligibly small.

Analyzing the Efficacy of the Relative Strength Indicator of Capital Inflows and Outflows Based on Big Data Analysis in Achieving Abnormal Returns Evidence from the Chinese Stock Market

This study originates from an analysis of market microstructure and introduces a novel statistical indicator of relative strength in capital flows through the application of big data analytics. This indicator effectively captures the impact of capital movements on future stock prices by integrating variations in stock prices with the volume of transactions within a corresponding timeframe. Building upon this foundation, the research develops an innovative momentum investment strategy based on the relative strength indicator of capital inflows and outflows, extending beyond the traditional fixed holding period momentum strategy framework. Empirical analysis reveals that this new indicator significantly demonstrates momentum effects in the Chinese A-share market; notably, in portfolios of stocks with smaller market capitalizations, the momentum strategy grounded on the new indicator achieves higher excess returns compared to traditional momentum strategies. These findings not only validate the efficacy of the new indicator but also underscore the critical role of big data analytics in enhancing the analysis of financial markets and the efficiency of investment decision-making.

Does audit quality moderate the relationship between financial statements readability and stock price crash risk?

Purpose This study aims to examine the correlation between the readability of financial statements and the likelihood of future stock price crashes in nonfinancial companies listed on the Egyptian Stock Exchange. It further explores the possible moderating effect of audit quality on this relationship. Design/methodology/approach The study uses ordinary least squares regression, generalized least squares estimation and two-stage least squares methodology to examine and validate the research hypotheses. The sample comprises 107 nonfinancial companies registered on the Egyptian Stock Exchange from 2016 to 2019. Findings The results reveal a significant negative association between the readability of financial statements and stock price crash risk. This suggests that companies with more complex financial statements tend to experience higher future crash risks. Additionally, the study identifies audit quality as a significant moderating factor. Higher audit quality, often indicated by engagements with Big-4 audit firms, strengthens the influence of financial statements readability on stock price crash risk. This implies that while high audit quality enhances investor confidence and market stability, it also accentuates the negative consequences of complex financial statements. Practical implications The findings of this paper have significant implications for regulators and standard-setting bodies in Egypt. They should consider refining and revising existing standards to emphasize the importance of enhancing the readability of financial reports. Additionally, auditing firms should actively engage in efforts to ensure clearer and more transparent financial reporting. These actions are vital for boosting investor confidence, strengthening Egypt’s capital market and mitigating potential risks associated with information opacity and complexity. Originality/value This study represents a pioneering endeavor within the Arab and Egyptian financial environments. To the best of the author’s knowledge, it is the first examination of the association between the readability of financial statements and stock price crash risk in these contexts. Furthermore, it explores factors such as audit quality that may influence this connection.

Predicting Petrol and Diesel Prices in Ghana, A Comparison of ARIMA and SARIMA Models

Predicting prices is of great concern and important in the world of economics and finance. In this paper, a comparative analysis of gasoline and diesel in Ghana were analysed using Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Based on their forecasting accuracy, the best model was used for predicting future prices of gasoline and diesel from January 2024 to December 2024. A monthly data for the prices of gasoline and diesel spanning from January 2016 to December 2023 taken from the Bank of Ghana (BoG) and the National Petroleum Authority (NPA) was used for the analysis. ARIMA (0; 1; 2) and ARIMA (2; 1; 3) were identified as the best models for gasoline and diesel respectively, SARIMA(0; 1; 2) x (0; 1; 1)12 and SARIMA (1; 1; 1) x (0; 1; 1)12 were also identified after taking a seasonal difference of the series all based on AIC and BIC. The coefficient of the identified models were tested for its significance using the Z-test. The ARIMA and the SARIMA models were compared using RMSE, MAE, and MAPE. The SARIMA models generally performed better than the ARIMA models for both gasoline and diesel except RMSE for diesel where the ARIMA model was slightly better than the SARIMA models with values of 0:9677988 and 1:011531 respectively. The model evaluation proved that the SARIMA models for both gasoline and diesel were superior to the ARIMA and showed that, the SARIMA model is adequate and appropriate for forecasting of prices of gasoline and diesel prices in Ghana.

Predicting energy prices based on a novel hybrid machine learning: Comprehensive study of multi-step price forecasting

Accurate prediction of energy prices is crucial to the development of energy security and environmental policies in various countries. This paper proposes a novel multi-step prediction hybrid model with genetic algorithm for variational mode decomposition, improved complete ensemble empirical modal decomposition with adaptive noise, bidirectional gated recurrent unit, temporal convolutional network, and multi-layer perceptron (GVMD-ICEEMDAN-BIGRU-TCN-MLP) for predicting carbon and natural gas futures prices. First genetic algorithm (GA) is used to fix the parameters of VMD model, the carbon and natural gas prices are decomposed into subsequences. Then the difference between the original series and the VMD after decomposition is further decomposed into subseries using ICEEMDAN. Next, the highest frequency series is predicted using the MLP model, and other subsequences are predicted using the BIGRU-TCN model. Finally, each predicted value is added linearly to determine the final result of steps 1, 3, and 5 of the entire forecasting process. According to the experimental results, it is shown that the model has lower prediction errors than the comparison model under mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R2), and modified Diebold-Mariano test (MDM). The good prediction results of the novel hybrid model are demonstrated in multi-step ahead integrated prediction experiments, especially in the experiments with 1-step ahead prediction, as well as in the experiments with varying training ratios.

Equity Analysis on IT Sector Stocks

The investment in share market is highly rewarding but highly risky. The concept of analysis comes into picture when decision must be made on choosing a particular company's shares for investment. Analysis includes fundamental analysis. Fundamental analysis is a method of forecasting the future price movements of a financial instrument based on economic, political, environmental, and other relevant factors and statistics that will affect the basic supply and demand. This paper examined fundamental analysis of IT sector of the selected companies from the Information Technology sector, since IT sector is one of the most upcoming sectors in the Indian Market Secondary Data of last 5 year (2019-2023). The sample of the stocks for the purpose of collecting secondary data has been selected based on Random Sampling. For analysis the monthly share prices of the last 5 financial years is collected for ten leading IT companies. for the study through fundamental analysis is carried out by tools like Economic analysis, Industrial analysis and Company Analysis Key ratios include ROA, ROI, ROE, EPS, DPS, dividend payout ratio, dividend yield, and P/E ratio. The stocks are chosen in an unbiased manner and each stock is chosen independent of the other stocks chosen. The major findings are all IT sector companies performing very well and their fundamentals are very strong based on P/E ratio, EPS and Payout ratio. It is recommended to the investor that to invest in IT sector company for long term will be benefited. Key Words: IT Sector, Fundamental Analysis, Investment, Equity, Market [1] Student, B. V. Patel Institute of Management, Uka Tarsadia University [2] Associate Professor, B. V. Patel Institute of Management, Uka Tarsadia University

Research on Machine Learning-based Prediction of Coffee Futures Prices

Coffee is one of the major agricultural commodities in world trade, and its futures are vital tools in the global capital market. The continued vitality of the coffee market and substantial price fluctuations have increased hedging demands among market participants. Consequently, predicting future price trends of coffee futures to yield excess returns has become a focal point in the field of quantitative investment. Machine learning methods are increasingly being applied in the field of quantitative investment due to their performance advantages in complex data classification and regression. This paper analyzes the current state of the coffee futures market and the factors influencing its prices. In this study, five market indicators and one technical indicator, the bias rate, were selected as inputs. The closing price for the subsequent day, along with short-term (50 days) and long-term (200 days) price trends, were forecasted using two machine learning techniques: the linear regression model and the random forest model. The results demonstrated that, of the two predictive models utilized in this study, the random forest model performed better concerning regression prediction evaluation indices. When predicting short-term (50-day) price trends, the linear regression model exhibited superior performance. However, both models revealed significant errors in predicting long-term (200-day) price trends.

Stock Trend Prediction and Analysis Based on Machine Learning

Stock trend prediction is a critically important activity in the financial sector. Investors aim to gain a better understanding of market dynamics, make wiser investment decisions, and manage investment risks more effectively by forecasting stock price trends. This is the focus of our upcoming research. This paper aims to utilize machine learning methods such as Support Vector Machines (SVM), based on spatial interval maximization strategies, Random Forest, based on multi-decision tree parallel learning strategies, and eXtreme Gradient Boosting (XGBoost), based on classification functions, to devise accurate classification function strategies for predicting and analyzing fluctuations in Dow Jones stock prices. Principal Component Analysis (PCA) will then be used to select some suitable features, identifying key factors with the greatest impact and minimal inter-correlation related to stock prices. Through a combination of various classification models, the research aims to forecast the future rise and fall of Dow Jones stocks. It has been observed that performing feature curation through PCA in advance enhances the predictive accuracy of different machine learning methods. Notably, the combination of PCA and XGBoost achieves the highest predictive rate. This approach provides a robust and scientifically grounded method for future stock price predictions and the formulation of trading strategies.

Research on Global Olive Oil Price Forecasting

Nowadays, commodity price forecasting has become a popular topic. The study of olive oil prices can inform pricing strategies and price positioning of olive oil. How to analyze the range and magnitude of price changes, as well as how consumers are likely to react to changes in olive oil prices, are important factors that will influence the future price trend of olive oil. Therefore, it is crucial for companies to set prices correctly. Since the ARIMA model has high forecasting accuracy and fewer parameters, the model has been chosen for most similar forecasts and is also chosen as a forecasting tool in this paper. The forecast results show that international olive oil prices will remain wildly high in the future, but the rate of increase will slow down. Since the data of recent years are heavily affected by COVID-19, the outliers of recent years also need to be dealt with if more accurate forecasts are needed, which is an unresolved issue in this paper. This paper also attempts to make some policy recommendations based on previous studies to moderate the rapid increase in olive oil prices.

Predicting and Analyzing the Bitcoin's Price with the ARIMA Model

Virtual currencies have become one of the most welcomed financial investment properties by investors, managers, and researchers. In this essay, we analyze the Bitcoin price from 2017 to 2023 and forecast the price of the Bitcoin. ARIMA model plays an important role in time series prediction, and many researchers choose to use this model to analyze and forecast historical time series. Therefore, this paper is based on the Autoregressive Integrated Moving Average Model (ARIMA) mode, by using the previous Bitcoin price to forecast the future price of Bitcoin. The outbreak of COVID-19 in late 2019 which then spread from China to the world has had a huge negative impact on the global economy. At the same time, owing to the impact of COVID-19 being significant, this paper will also analyze the influence of the pandemic’s influence on Bitcoin. The result shows that the epidemic has a great influence on it and reflect a different consequence of other industry. Investors and others should be cautious about investing in bitcoin.

Flight Price Prediction Web-based Platform: Leveraging Generative AI for Real-time Airfare Forecasting

The aviation business encounters difficulties in correctly and swiftly predicting flight fares due to the dynamic nature of the sector. Factors such as variations in demand, fuel costs, and the intricacies of various routes have an impact on this. This work presents a new method to tackle this issue by utilizing generative artificial intelligence (GAI) approaches to accurately forecast airfares in real-time. This paper presents a novel framework that integrates generative models, deep learning architectures, and historical pricing data to improve the precision of future flight price predictions. The study employs a GAI within a cutting-edge web engineering framework. This approach is designed primarily to gather knowledge about complex patterns and relationships present in historical airline data. Through the utilization of this methodology, the model is able to accurately perceive complex connections and adjust to ever-changing market conditions. Our model utilizes deep neural networks to effectively handle various circumstances and extract vital information, so facilitating a comprehensive comprehension of the intricate elements that impact flight cost. Moreover, the suggested approach places significant emphasis on precisely predicting upcoming occurrences in real-time, facilitating prompt reactions to market volatility and offering a valuable resource for airlines, travel agents, and customers alike. In order to enhance the accuracy of real-time forecasts, we utilize a web-based platform that allows for smooth interaction with live data streams and guarantees swift updates. The results demonstrate the model’s capacity to adjust to dynamic market conditions, rendering it an attractive option for stakeholders in search of precise and current forecasts of flight prices.

НЕЙРОМЕРЕЖЕВЕ ПРОГНОЗУВАННЯ ЦІН НА ФОНДОВОМУ РИНКУ

In the modern world of financial markets are showing more and more interest in systems that can accurately and efficiently predict the future price of financial instruments. Information technologies that exist at the moment make it possible to analyze and use highly loaded systems such as neural networks to predict the financial performance of a company. This article discusses the use of neural networks to predict the price of shares in the financial market. The possibilities of neural networks for predicting stock prices are considered due to the fact that neural networks have many hidden blocks that allow the model to adapt to complex relationships between company indicators and its stock price. An example of a RNN neural network is given that can work with sequential data such as hourly series. For an example of building a model, Apple was chosen as one of the largest companies that is included in the S&P 500 list of the most influential companies in the American market.

Forecasting Agriculture Commodity Futures Prices with Convolutional Neural Networks with Application to Wheat Futures

In this paper, we utilize a machine learning model (the convolutional neural network) to analyze aerial images of winter hard red wheat planted areas and cloud coverage over the planted areas as a proxy for future yield forecasts. We trained our model to forecast the futures price 20 days ahead and provide recommendations for either a long or short position on wheat futures. Our method shows that achieving positive alpha within a short time window is possible if the algorithm and data choice are unique. However, the model’s performance can deteriorate quickly if the input data become more easily available and/or the trading strategy becomes crowded, as was the case with the aerial imagery we utilized in this paper.

Potentials of Mixed-Integer Linear Programming (MILP)-Based Optimization for Low-Carbon Hydrogen Production and Development Pathways in China

Hydrogen (H2) is considered one of the main pillars for transforming the conventional “dark” energy system to a net-zero carbon or “green” energy system. This work reviewed the potential resources for producing low-carbon hydrogen in China, as well as the possible hydrogen production methods based on the available resources. The analysis and comparison of the levelized cost of hydrogen (LCOH) for different hydrogen production pathways, and the optimal technology mixes to produce H2 in China from 2020 to 2050 were obtained using the mixed-integer linear programming (MILP) optimization model. The results were concluded as three major ones: (a) By 2050, the LCOH of solar- and onshore-wind-powered hydrogen will reach around 70–80 $/MWh, which is lower than the current H2 price and the future low-carbon H2 price. (b) Fuel costs (>40%) and capital investments (~20%) of different hydrogen technologies are the major cost components, and also are the major direction to further reduce the hydrogen price. (c) For the optimal hydrogen technology mix under the higher renewable ratio (70%) in 2050, the installed capacities of the renewable-powered electrolysers are all more than 200 GW, and the overall LCOH is 68.46 $/MWh. This value is higher than the LCOH (62.95 $/MWh) of the scenario with higher coal gasification with carbon capture and the storage (CG-CCS) ratio (>50%). Overall, this work is the first time that hydrogen production methods in China has been discussed comprehensively, as well as the acquisition of the optimal H2 production technology mix by the MILP optimization model, which can provide guidance on future hydrogen development pathways and technology development potential in China.

The capital market consequence of sustained abnormal Audit fees: Evidence from stock price crash risk

Prior studies provide mixed interpretations for the effect of abnormal audit fees on audit quality. One interpretation is that abnormal audit fees reflect economic bonding which decreases audit quality, while the other interpretation is that they are associated with unobserved audit efforts and audit risk. We argue that long-term abnormal audit fees clarify mixed evidence, as they reflect the gradual formation and development of both economic bonding and sustained auditor efforts over time. We examine the effect of long-term abnormal audit fees on audit quality by focusing on client's future stock price crash risk. Using 42,604 firm-year observations of U.S. firms, we find that sustained positive abnormal audit fees (consistently positive long-term abnormal audit fees) are negatively associated with future stock price crash risk, supporting the auditor effort argument and negating the economic bonding argument. We also find weak evidence that current-period abnormal audit fees are positively associated with future stock price crash risk, supporting the audit risk argument. Overall, our evidence shows that the magnitude and the pattern of long-term abnormal audit fees jointly affect audit quality in mitigating a client's bad news hoarding behavior.

Measuring the Efficiency of State-Owned Stocks Using Capital Asset Pricing Model (CAPM)

Abstract Research aim : This study examines market efficiency using the Capital Asset Pricing Model (CAPM) method on BUMN stocks in Indonesia. Design/Methode/Approach : This model explains the relationship between risk and return in an efficient market. The analysis focuses on using stock beta calculations for 5 years. Research Finding : The research results are as follows: 1) the BUMN stock market in Indonesia is classified as efficient, namely 11 stocks where 5 companies have positive individual returns, namely ANTM, TINS, KRAS, BBNI, and PGAS. There are 6 companies that have negative returns, namely WSKT, ADHI, WIKA, PTPP, SMBR, and BBTN. 2) the analysis was carried out during the covid-19 pandemic period, the basic material sector is a collection of stocks that are classified as resilient during the pandemic showing positive and efficient returns. 3) overall, there is a high systematic risk of BUMN stocks in Indonesia, and actively responds to any changes that occur in market prices. Theoretical contribution/Originality : This contribution is expected to be a reference for investors and market participants. Practitionel/Policy implication : These results provide information for investors to choose efficient State-Owned Enterprises (BUMN) stocks in deciding to invest and still consider the nature and characteristics of each investor. Research limitation : Future research is expected to use other methods in analyzing the level of stock risk such as Arbitrage Pricing Theory (APT) or estimating future stock prices using the ARIMA / GarCH forecasting method and increasing the number of samples in the study or different market indices so that the expected results are more accurate in predicting future stock prices.

Crash risk and conservatism: Evidence from Borsa Istanbul

This study assesses the relationship between the likelihood of future stock price crashes and conservatism—an accounting characteristic that leads to the undervaluation of accounting net assets relative to economic net assets. This undervaluation is achieved by less stringent verification criteria in acknowledging losses compared with gains, resulting in more timely recognition of economic losses. Utilizing a sample of firms traded on Borsa Istanbul from 2009 to 2019, this study reveals that firms with a greater degree of conservatism witness a significant reduction in crash risk after accounting for firm-specific determinants of crash risk along with firm and year fixed effects. This result corroborates the findings in the literature on conservatism, revealing that conservatism diminishes the ability of managers to withhold unfavorable information. In addition, the results are economically meaningful and hold after a set of tests to assess robustness. The findings are particularly relevant for underperforming firms, indicating that an increase in adverse information enhances the motivation for firms to obscure and delay sharing the information. Further analysis demonstrates that accounting conservatism offers advantages by mitigating future crash risk, especially for firms with high intangible intensity.

Minimum, Maximum, and Average Implementation of Patterned Datasets in Mapping Cryptocurrency Fluctuation Patterns

Cryptocurrency price fluctuations are increasingly interesting and are of concern to researchers around the world. Many ways have been proposed to predict the next price, whether it will go up or down. This research shows how to create a patterned dataset from an API connection shared by Indonesia's leading digital currency market, Indodax. From the data on the movement of all cryptocurrencies, the lowest price variable is taken for 24 hours, the latest price, the highest price for 24 hours, and the time of price movement, which is then programmed into a pattern dataset. This patterned dataset is then mined and stored continuously on the MySQL Server DBMS on the hosting service. The patterned dataset is then separated per month, and the data per day is calculated. The minimum, maximum, and average functions are then applied to form a graph that displays paired lines of the movement of the patterned dataset in Crash and Moon conditions. From the observations, the Patterned Graphical Pair dataset using the Average function provides the best potential for predicting future cryptocurrency price fluctuations with the Bitcoin case study. The novelty of this research is the development of patterned datasets for predicting cryptocurrency fluctuations based on the influence of bitcoin price movements on all currencies in the cryptocurrency trading market. This research also proved the truth of hypotheses a and b related to the start and end of fluctuations.

Application of the Support Vector Regression Method with the Grid Search Algorithm to Predict Movement Gold Price

Gold is an investment with the smallest risk because it can be sold anytime and anywhere. In Indonesia, gold bullion as an investment product is known for its purity level of 99.99%, namely gold bullion produced by PT. Aneka Tambang (Antam) through its Precious Metals business unit. Apart from its pure production, Antam gold bullion is easier to resell anytime and anywhere because it has an official certificate from the international gold standardisation institution, namely LBMA (London Bullion Market Association), to more easily estimate the value of gold bullion when sold. To overcome this, predictions of future gold prices are needed. In this research, one of the prediction methods is Support Vector Regression with the Grid Search Algorithm. In this method this method will be used to predict the price of gold, which aims to predict and find out the price of gold one year in the future to produce a level accuracy (MAPE) of 5.43% and the prediction of gold prices increasing from 2023-June-01 to 2024-March-23 while experiencing a decline starting in 2024-March-24. Research by examining the relationship between variables, which emphasises data consisting of numbers so that it is analysed based on statistical procedures using the Support Vector Regression method with data sourced from the daily price of gold bullion through PT. Gallery 24 Pawnshops, North Sumatra. Where this method is very well used in predicting by choosing the best kernel used is the linear kernel because, from these three kernels, the best hyperparameters were obtained for predicting gold price movements using a linear kernel with a division for training and testing data of 60: 40. The MAPE value obtained was 5.43.

Research on Supermarket Replenishment Pricing Decision Making Based on BP Neural Network and Greedy Algorithm

The aim of this paper is to provide strong support for superstores through a data-driven approach. By analyzing and fitting the sales history data of each category and individual product, this paper uses BP-neural network model to predict the sales volume and transforms the replenishment problem into a knapsack problem, so as to plan the future pricing strategy and replenishment volume of the superstore. This helps to optimize the category structure of the superstore, increase the profit margin, reduce the wastage rate, and improve the service quality.