Price Fluctuations Research Articles

ЭКОНОМИЧЕСКИЙ ПОРТРЕТ КАЗАХСТАНА: НОВЫЕ ВЕХИ

Recent years have been marked by steady growth of the Kazakh economy, which is supported by the dynamic development of key sectors and the active introduction of new technologies. In 2024, the country continues to successfully adapt to the changing global economic environment, including commodity price volatility and global economic turmoil. The Kazakh economy has demonstrated steady positive dynamics, which is due to the stable growth of key industries and innovative development. Despite global economic challenges and fluctuations in commodity prices, the country continues to demonstrate adaptability and sustainability of economic growth in 2024. International financial institutions and analytical centers agree that the Kazakh economy will maintain moderate growth rates in 2024. This indicates a gradual recovery from global economic turmoil. An important factor contributing to such development is the diversification of the economy, aimed at reducing dependence on commodity exports and stimulating domestic consumption, infrastructure projects and innovation. The Kazakh government is actively working to improve the country's investment attractiveness, support small and medium-sized businesses and develop human capital. These measures are aimed at ensuring sustainable economic growth and improving the well-being of the population. This article provides an in-depth analysis of the current economic state of Kazakhstan, including the dynamics of GDP and GRP, as well as development prospects.

Quantum Variational Autoencoders for Predictive Analytics in High Frequency Trading Enhancing Market Anomaly Detection

High-frequency trading (HFT) markets, characterized by high and frequent price fluctuations, necessitate the use of anomaly detection mechanisms to monitor the market and ensure the efficacy of the trading system. This paper aims to discuss the possibility of improving predictive analytics in HFT using quantum computing with the help of the Quantum Variational Autoencoder (QL-VAE). As a result, we propose a new direction for further research on quantum VAEs in HFT that involves their direct comparison with classical VAEs. The application of quantum models for mastering the intensive data flow of HFT is conditioned by the advantages of quantum computation in comparison to classical ones, which are more suitable for handling multidimensional data arrangements and intricate topologies. Our detailed study methodology involved examining various aspects of HFT data, such as order book features and stock price characteristics. We normalized all the data and reduced some of its dimensions. We established quantum VAEs using Pennylane, and configured the classical VAEs using TensorFlow. When it comes to market anomalies, the results of the comparative analysis showed higher accuracy, recall, and F1 rate in quantum VAEs compared to classical models when it comes to the analysis of market anomalies. Therefore, the quantum model's ability to handle high-dimensional data makes it a better fit for HFT than classical methods. These studies suggest that quantum VAEs could significantly improve anomaly detection in the financial market.

An Economic Analysis of Coal Pricing in Mongolia

Coal is a critical export for Mongolia, playing a significant role in the nation’s economy by contributing to GDP and export revenues. This paper provides an economic analysis of coal pricing in Mongolia, examining the primary factors that drive price fluctuations in both domestic and international markets. Key areas of focus include global demand, particularly from neighboring China, transportation costs, government policies, currency exchange rates, and environmental regulations. The paper employs a mixed-method approach, analyzing historical price data alongside policy reviews to identify the challenges and opportunities Mongolia faces in stabilizing coal prices. Global coal demand, especially from China, has a profound effect on Mongolian coal prices, while infrastructure limitations and transportation costs further exacerbate price volatility. Additionally, Mongolia’s coal sector is influenced by international competition, particularly from established exporters like Australia and Indonesia, which benefit from more developed supply chains. This research aims to provide valuable insights for policymakers and stakeholders by offering recommendations on how Mongolia can enhance price stability and strengthen its position in the global coal market. By analyzing the economic forces shaping Mongolian coal prices, the study contributes to broader discussions on resource management and economic sustainability in coal-dependent economies. The findings will aid policymakers in developing strategies that address Mongolia's infrastructure challenges and ensure the long-term viability of its coal industry in the face of evolving global energy dynamics.

News-Driven Volatility: A Deep Dive into Leading Nifty Healthcare Stocks

This study conducts a comprehensive analysis of stock price volatility within the healthcare sector, concentrating on five prominent companies: Sun Pharma, Dr. Reddy, Cipla, Apollo Hospitals, and Divis Laboratories. Leveraging annual daily data from the Nifty Healthcare Index for 2023, the research delves into the intricate relationship between stock price fluctuations and market-sensitive news events. Employing a robust methodology that integrates slope calculations, ANOVA, Tukey’s HSD tests, moving averages, and standard deviation metrics, the study evaluates the differential impact of these events on stock volatility. The findings reveal significant volatility, with Apollo Hospitals demonstrating the highest levels of price variability. The research highlights the profound influence of regulatory shifts, financial performance metrics, and macroeconomic conditions on stock behavior. These insights are pivotal for investors and financial analysts seeking to navigate the complex dynamics of the healthcare market. The application of moving averages further refines the analysis, offering a sophisticated lens through which to assess and interpret market trends, ultimately enhancing the strategic decision-making process within this critical sector.

A Robust numerical technique based on the chromatic polynomials for the European options regulated by the time-fractional Black–Scholes equation

AbstractRisk mitigation and control are critical for investors in the finance sector. Purchasing significant instruments that eliminate the risk of price fluctuation helps investors manage these risks. In theory and practice, option pricing is a substantial issue among many financial derivatives. In this scenario, most investors adopt the Black–Scholes model to describe the behavior of the underlying asset in option pricing. The exceptional memory effect prevalent in fractional derivatives makes it easy to understand and explain the approximation of financial options in terms of their inherited characteristics prompted by the given reason. Finding numerical solutions that are both successful and suitably precise is crucial when working with financial fractional differential equations. Hence, this paper proposes an innovative method, designated the Chromatic polynomial collocation method (CPM), for the theoretical study of the Time fractional Black–Scholes equation (TFBSE) that regulates European call options. The newly developed numerical algorithm CPM is on a functional basis of the Chromatic polynomials of Complete graphs (Kn) and operational matrices of the basis polynomials. The CPM transforms the TFBSE into a framework of nonlinear algebraic equations with the help of operational matrices and equispaced collocation points. The fractional orders in the PDE are concerned in the Caputo sense. The CPM findings further corroborate the results of the most recent numerical schemes to show the effectiveness of the suggested numerical algorithm.

PERBANDINGAN FUZZY TIME SERIES MARKOV CHAIN DAN FUZZY TIME SERIES CHENG

Investing is a hot and fast-growing topic right now. Stock.investing.is one of the most popular investments by the public. The JCI is an index that measures the performance of all stocks listed on the IDX. The closing price of the stock is published daily and can be used by investors as an investment benchmark. The occurrence of stock price fluctuations entails a high risk of loss. Predicting stock prices is one way to avoid this risk. Fuzzy time series is a time series model that can be used to minimize the risk of future occurrences. Time parameter data is not stationary, so this research uses fuzzy time series with Markov chains and Cheng's method to determine the JCI completion dates from January 2018 to June 2022. Calculating the accuracy level of the two method approaches using symmetric Mean Absolute Percentage Error (sMAPE), the sMAPE value obtained in the Fuzzy Time Series Markov Chain method is 2.11% and the Fuzzy Time Series Cheng method is 2.98%. The conclusion is that of the two methods the Markov Chain has a smaller value and can be said to be a better method compared to the Cheng method.

The Influence of Economic Variables on Stock Prices of Telecommunications Companies

The general background fluctuation of stock prices is a critical concern for investors, particularly in dynamic economic environments where various indicators can significantly impact financial performance. The specific background of this study focuses on the telecommunications sector, which has been increasingly influenced by economic variables such as the Inflation Rate, SBI Interest Rate, Earnings Per Share, Rupiah Exchange Rate, and Company Fundamentals. Despite existing research, there is a knowledge gap regarding how these factors collectively influence stock prices in publicly listed telecommunications companies. This study aims to investigate the effects of these economic variables on stock prices from 2020 to 2023, utilizing a quantitative approach with secondary data obtained from annual financial reports of 16 companies. The results demonstrate that all examined variables—Inflation Rate, SBI Interest Rate, Earnings Per Share, Rupiah Exchange Rate, and Company Fundamentals—significantly affect stock prices. The novelty of this research lies in its comprehensive analysis of the interplay between these economic indicators specifically within the telecommunications sector. The implications of these findings suggest that investors and policymakers should consider these economic factors when making investment decisions, thereby enhancing their financial strategies and contributing to a more robust understanding of stock market dynamics in the telecommunications industry. Highlights: All examined economic variables significantly affect stock prices. The study analyzes data from 16 publicly listed telecommunications companies. Findings enhance investment strategies and understanding of market dynamics. Keywords: Inflation, Interest Rate, Earnings Per Share, Exchange Rate, Stock Price

Design, simulation and feasibility of the innovative agricultural warehouse receipt system through dynamic programming and agent-based models.

To address marketing challenges in the agricultural sector, provide financial support for small-scale farmers over marketing seasons, manage price risks of agricultural products, and enhance the functioning of agricultural mercantile exchanges, it is attainable to implement an efficient and compliant warehouse receipt system (WRS) that aligns with the legal, institutional, social, and economic-financial conditions of a country. The aim of this study is to design, simulate, and assess the feasibility of an innovative WRS in the agricultural sector. To achieve this, a WRS was designed and evaluated for maize crop in Iran. The research methodology of this study is divided into three main parts: design, simulation, and feasibility assessment of the WRS. The design process incorporated the FAO-provided (2009) warehouse receipt system development, considering the experiences of various countries and the institutional and financial regulations specific to Iran. Additionally, a dynamic programming model was used to simulate the system, and an agent-based model was utilized for system feasibility assessment. The study results demonstrated that it is possible to design an innovative and efficient WRS by involving five key actors, including farmers, buyers (maize traders), banks, mercantile exchange market, and the warehouse (governmental institution), and establishing clear communications among them. Based on simulation results using dynamic programming model, it was evident that four parameters, namely the annualized loan interest rate, the valuation coefficient for loan collateral, price volatility of the product over the marketing season, and the warehouse cost-to-product value ratio, significantly impact the adoption of the WRS by farmers. In conclusion, the findings from the agent-based model revealed that setting the annualized loan interest rate at 8%, a collateral valuation coefficient of 85%, price fluctuations over the non-harvest time at 60%, and a warehouse cost-to-product value ratio of 2% can result in the participation of nearly 100% of farmers in the proposed WRS.

A Survey of Data-Driven Construction Materials Price Forecasting

The construction industry is heavily influenced by the volatility of material prices, which can significantly impact project costs and budgeting accuracy. Traditional econometric methods have been challenged by their inability to capture the frequent fluctuations in construction material prices. This paper reviews the application of data-driven techniques, particularly machine learning, in forecasting construction material prices. The models are categorized into causal modeling and time-series analysis, and characteristics, adaptability, and insights derived from large datasets are discussed. Causal models, such as multiple linear regression (MLR), artificial neural networks (ANN), and the least square support vector machine (LSSVM), generally utilize economic indicators to predict prices. The commonly used economic indicators include but are not limited to the consumer price index (CPI), producer price index (PPI), and gross domestic product (GDP). On the other hand, time-series models rely on historical price data to identify patterns for future forecasting, and their main advantage is demanding minimal data inputs for model calibration. Other techniques are also explored, such as Monte Carlo simulation, for both price forecasting and uncertainty quantification. The paper recommends hybrid models, which combine various forecasting techniques and deep learning-advanced time-series analysis and have the potential to offer more accurate and reliable price predictions with appropriate modeling processes, enabling better decision-making and cost management in construction projects.

Pentingnya Kualitas Pelayanan dan Kepercayaan Konsumen Terhadap Loyalitas Pelanggan di CV Putra Timur Farm

In the constantly shifting and challenging market landscape, one notable phenomenon is the surge in new businesses. This study focuses on examining the impact of service quality and consumer trust on customer loyalty at CV Putra Timur Farm. In the commodity business, where prices frequently fluctuate, maintaining customer loyalty is essential for business sustainability. Data for this research was collected through observations and questionnaires and analyzed using the Structural Equation Modeling (SEM) Partial Least Squares (PLS) method. The results of the analysis indicate that excellent service quality and high levels of consumer trust have a positive and significant effect on customer loyalty. The findings highlight the critical importance of improving service quality and building strong consumer trust to maintain and enhance customer loyalty, especially amid unpredictable price fluctuations in commodity markets. This research underscores the need for businesses to focus on service excellence and trust-building strategies to ensure long-term customer retention and overall business success

Forecasting the Volatility of Tuna Fish Prices in North Sumatra using the ARCH Method in the Period January - April 2024

Tuna (Euthynnus affinis) is one of the most important fisheries commodities in Indonesia with significant economic value, especially in its contribution to fisheries export revenue. However, the price of tuna experiences significant fluctuations that can affect local and national economic stability. This study analyzes the daily price fluctuations of tuna in the North Sumatra market from January 1, 2024 to April 29, 2024 using a time series analysis approach. Daily price data were collected and analyzed to identify existing price patterns and volatility. The Autoregressive Conditional Heteroskedasticity (ARCH) model was selected to address the heteroscedasticity in the data, which suggests that the volatility of tuna prices can be well predicted based on past price behavior. The analysis steps include identifying the optimal ARCH model using the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF), as well as testing parameter significance and normality assumptions to validate the model fit. The results show that the ARMA (1,0,0) model is the optimal one to model the price volatility of yellow tuna with the MAPE obtained of 2.382. compared to the ARMA-ARCH method with the MAPE value obtained of 2,747. Because it still contains heteroskedasticity effects, even though the results are good, the prediction results do not closely match the original data. The model is effective in improving price forecasting accuracy, which is important to support decision-making in risk management and economic planning in the fisheries sector. The findings contribute to understanding the dynamics of the yellowtail market and optimizing strategies for fisheries management.

Electrification of transportation: A hybrid Benders/SDDP algorithm for optimal charging station trading

This paper examines the electrification of transportation as a response to environmental challenges caused by fossil fuels, exploring the potential of battery electric vehicles and hydrogen fuel cell vehicles as alternative solutions. However, a significant barrier to their widespread adoption is the limited availability of charging infrastructure. Therefore, this study proposes the development of comprehensive charging stations capable of accommodating both battery and hydrogen vehicles to address this challenge. The energy is purchased from the day-ahead and intraday auction-based electricity markets, where the electricity price is subject to uncertainty. Therefore, a two-stage stochastic programming model is formulated while the price scenarios are generated utilizing a k-means clustering algorithm. Given the complexity of the proposed model, an efficient solution approach is developed through the hybridization of the Benders decomposition algorithm and stochastic dual dynamic programming. In the Benders master problem, day-ahead bidding variables are determined, whereas the Benders sub-problem addresses intraday bidding and charging station scheduling variables, employing stochastic dual dynamic programming to tackle its intractability. Additionally, we transform the mixed integer linear program model of the second stage problem into a linear program, confirming its validity through KKT conditions. Our model provides practical insights for making informed decisions in electricity markets based on sequential auctions. While the bidding curves submitted to the day-ahead market remain unaffected by scenarios, those submitted to the intra-day market show dependence on fluctuations in day-ahead market prices.

Thermo-economic analysis of a solar district heating plant with an air-to-water heat pump

Solar district heating systems are essential in reducing carbon emissions and alleviating the energy crisis. By integrating with air-to-water heat pumps, it is possible to enhance the system’s efficiency and flexibility. However, the complementary mechanisms and coupling effects between the heat pump and the other components of the system are not clear. To address these issues, it is necessary to investigate the thermo-economic performance of the system, taking into account energy price fluctuations to achieve a more efficient and economically viable operational model. This study focuses on a solar district heating system in the Danish city of Ørum and investigates the impact of integrating a large-scale air-to-water heat pump. Based on energy and economic analyses, the impact of the heat pump on the system efficiency and the levelized cost of heat are investigated for 2020 and 2022. The results show that the heat pump can convert low-cost electricity into heat which will be stored in the tank, increasing the tank’s heat storage content by 1.2 times. The medium to low-temperature water in the tank can preheat the heat pump’s compressor, raising the COP of the heat pump from 3.3 to 3.5 and increasing the annual utilization cycle of the tank by 1.4 times by reducing the return water temperature to the bottom of the tank. Additionally, the system performance has been improved due to the installation of the heat pump, which increased the system COP from 1.22 in 2020 to 2.62 in 2022. Subsequently, the CO2 emission has been decreased from 192 kg/MWh to 74 kg/MWh with a larger share of sustainable energy. Due to the heat pump operation, the system-levelized cost of heat could be reduced to 68.6 EUR/MWh, compared to 94 EUR/MWh if the heat pump is removed. The investigation also revealed that the heat pump improved the flexibility of the heating system in response to energy prices, especially during the 2022 energy crisis in Europe. The findings of the paper provide a good reference for large solar heating applications.

Performance of natural asphalt as a paving material: A laboratory and field evaluation

The ever-growing need to build roads to meet the necessary transportation demands is challenging, especially for developing countries. Low-volume roads (LVRs) are usually the backbone of catalyzing economic growth in these countries. With impediments surrounding Petroleum bitumen (price fluctuations) and environmental concerns, scientists are putting their effort into finding an alternative. The presented research is an attempt to check if Natural asphalt can be used as a full or partial replacement of the Petroleum bitumen. To the best of the authors' knowledge, only limited studies have focused on characterizing and understanding the engineering properties of Natural asphalt. The available techniques do not provide reliable information to the road authorities and hence they are discouraged from using it in practice. Particularly for countries, where the Natural asphalt source is available, the overall dependence on importing the Bitumen could be substantially reduced. Empirical and experience-based design criteria may not be sufficient as the standards were never developed for such materials, hence, a scientific approach is required before bringing it into practice. In this research, Natural asphalt sourced from different locations in Nigeria was assessed. Before performing the mixture level tests using Marshall and Cantabro design methods, the rheological and fatigue properties of the extracted Natural bitumen were examined in the laboratory. In the design of the experiment, various percentages of Natural asphalt were added between 0 % and 20 % by total mix weight; implying that the remaining required fraction of binder was fulfilled by the addition of petroleum bitumen. By using a ranking system (supported by statistics), an optimal design of mixture was obtained which was used in the field (exposed to normal traffic) at 30 different sections. Overall, results showed a good correlation between laboratory and field performance as compared to the petroleum-based mixture which was used as a reference mixture

Exploring vehicle preference dynamics: Analyzing the influence of oil price volatility on consumer car purchase decisions - A comparative survey experiment

China's automobile market is continuously expanding, leading to ongoing growth in oil demand. Fluctuations in oil prices will inevitably impact the travel patterns and car purchasing behavior of automotive consumers. This paper analyzes the influence of gasoline price fluctuations on the travel patterns and car purchasing behaviors of auto consumers with varying incomes, employing a dynamic perspective. We conducted a questionnaire survey of auto consumers in four first-tier cities in China and performed a comparative analysis of questionnaire data from 2015 to 2022. The empirical findings are as follows: (1) Under conditions of elevated oil prices, fuel car consumers exhibit an increased susceptibility to oil price fluctuations, which may cause fuel car consumers to curtail their travel activities. (2) The 10 yuan/liter is the threshold for middle - and upper-income consumers to change their car buying or travel habits, which has not been affected by oil price fluctuations. (3) For the cohort considering electric vehicles, gasoline prices stand as the primary determinant influencing their car buying choices. The primary conclusions serve as significant references for the government to craft corresponding carbon emission reduction policies amidst fluctuating oil prices.

Assessment of Garcinia kola Heckl value chain and its contribution to the livelihoods of local populations in Eastern Cameroon

The value chain analyses of a product can provide vital information for improving the production, value addition, market organization and boost the contribution of the product to the income of the stakeholders involved. Hence, this study was carried out on the Garcinia kola value chain in Belabo, Cameroon. Twenty-three focus group discussions were held, and semi-structured surveys were administered to 135 stakeholders engaged in the G. kola value chain in the Belabo municipality. The results reveal that nuts, barks, and roots are the main parts collected. The nuts are marketed without processing while the barks and roots are consumed directly, marketed or processed into powder before consumption and marketing. G. kola value chain in Belabo has two levels of structuring, rural and urban. Nuts are sold by the unit or in buckets corresponding to the kilogram, with the price per nut ranging from 0.4 to 1.70 USD, depending on whether you're in the rural or urban market. It also varies according to production season and nut size. Barks and roots are sold all year round, generally in piled strips weighing approximately 100 g, with prices ranging from 0.17 to 1.75 USD on the rural and urban markets, respectively. The main stakeholders involved in the value chain are collectors/harvesters, local traders, retailers and wholesalers. Marketing provides more income to wholesalers and retailers, contributing over 35 % and 20 % to their annual income and less than 30 % and 15 %, respectively, to those of collectors and local traders. The major problems the G. kola value chain in this locality is facing are the attack of the product by weevils (24 % of citation), poor storage facilities and deforestation (14 %), price fluctuation, and lack of market (13.33 and 11.85 %). In Belabo, the marketing of G. kola is not profitable for the collectors, who are the main actors in the production chain characterized by rudimentary processing, poor storage and preservation techniques high marketing. The organization of the different stakeholder into association would help to better structuring the G. kola value in Belabo are the two main opportunities for improving the G. kola value chain with the potential of increase its contribution to the livelihoods of the different main stakeholders involved. In addition, policymakers should consider initiating innovations to boost production, support conservation, processing and price regulation to scale up economic and environmental benefits from G. kola.

Sustainable soil management practices provide additional benefit for energy use efficiency

In light of recent fluctuations in energy prices, there has been a growing emphasis on energy efficiency within the agricultural sector. At the same time, ongoing soil degradation in intensive agricultural systems reinforced the need for soil health improving agricultural practices. This study combines the two aspects and examines the effects of sustainable soil management practices on total energy consumption, specifically focusing on fertilizer and pesticide energies, as well as economic indicators such as contribution margins. Using Germany as a case study, we assess three general soil improving management practices: diversified crop rotations, organic fertilizers (green or liquid manure) instead of mineral fertilizers, and no-till/reduced till systems instead of ploughing. Drawing on data from the Kuratorium für Technik und Bauwesen in der Landwirtschaft e.V. (KTBL) (Board of Trustees for Technology and Construction in Agriculture) database for German agricultural planning, we consider variations in yield potentials, soil types, and farming systems. Our results reveal that using mineral fertilizers and shifting to more diverse crop rotations can reduce energy consumption by approximately 21,000 MJ/ha on average (7 % of total energy) over a 6-year rotation. Likewise, adopting no-till systems instead of ploughing decreases energy use by 12,000 MJ/ha (5 % of total energy). Economically, organic farming offers a €4000/ha higher contribution margin compared to conventional methods in fertilization and tillage. These sustainable practices improve soil health, conserve energy, and enhance economic viability. With fluctuating energy prices, organic farming could become more economically attractive and accelerate its adoption across agricultural landscapes.

Growth, Instability in Production and Price Forecasting of Onion in Bangladesh

Onion is an essential and popular spice crop which is widely cultivated and consumed in Bangladesh. Every year the country needed to import onion for fulfilling the domestic demand. Onion price has been largely influenced by import price and frequent fluctuation. The objectives of the research were to analyze the onion production behavior, instability, and forecasting of price using secondary data. The study used deterministic growth models and coefficient of variation for analyzing the growth rate and instability. Among different growth models, cubic model was identified as the best-fitted model. The average growth rate was 7.85%, and in instability analysis the coefficient of variation was 71.10%, which implies that onion production was unstable during the period of 1970-2022. Seasonal Autoregressive Integrated Moving Average (SARIMA) model was used to forecast onion price. The finding reveals that SARIMA (1, 0, 2) (1, 1, 1)12 model identified as the best model to forecast the onion price in Bangladesh. The results show that onion price followed seasonal trend, and the highest price was in October and November. These findings will support to develop appropriate policies regarding the increase of domestic supply through increased production and storage facilities, reducing post-harvest losses, and price stabilization. J Bangladesh Agril Univ 22(3): 377-385, 2024

Does oil price uncertainty affect corporate total factor productivity? Evidence from China

In the era of high-quality economic development, oil price volatility (OVX) and the total factor productivity (TFP) of corporations are pivotal issues for both policymakers and scholars. This study leverages the implied volatility of oil prices and financial data from Chinese listed industrial companies spanning 2010 to 2022 to investigate the influence of OVX on firms’ TFP and the underlying mechanisms. The findings reveal that OVX substantially dampens firms’ TFP, with corporate leverage and financialization identified as key channels through which this impact occurs. Further heterogeneity analysis indicates that the negative impact of OVX on TFP is particularly pronounced in firms operating in industries with low concentration and among small and medium-sized enterprises (SMEs). The extension analysis suggests a threshold effect in the relationship between OVX and corporate TFP, with the suppressive effect of OVX on TFP intensifying as the level of corporate financialization increases. Consequently, it is imperative for policymakers to closely monitor oil price fluctuations and implement timely strategies to mitigate the risks associated with OVX.

Stock Price Prediction and Investment Simulation - Based on SSA-CNN-LSTM Method

Stock price fluctuations, which are time-series in nature. At the same time, based on the machine learning Long Short-Term Memory Network (LSTM) has excellent processing ability in predicting long time series, this paper proposes a stock price prediction method using CNN-LSTM optimized for LSTM hyperparameters using Sparrow algorithm. The data used in this study covers a total of 3403 trading days from March 1, 2010 to March 29, 2024 and about 40 technical indicator factors were selected. CNN model was firstly used to obtain features in the data. And later, CNN-LSTM network using SSA for parameter optimization uses the extracted features for stock price prediction and simulated trading based on the predicted up and down signals. The experimental results show that the SSA-CNN-LSTM network is able to provide better prediction accuracy than the CNN-LSTM network for price derivation. This prediction method not only provides a better op-eration idea for actual trading, but also provides practical experience for scholars to study time se-ries in finance.