Search Results (65)

Recent years have seen a rise in combining deep learning and technical analysis for stock price prediction. However, technical indicators are often prioritized over technical charts due to quantification challenges. While some studies use closing price charts for predicting stock trends, they overlook charts from other indicators and their relationships, resulting in underutilized information for predicting stock. Therefore, we design a novel framework to address the underutilized information limitations within technical charts generated by different indicators. Specifically, different sequences of stock indicators are used to generate various technical charts, and an adaptive relationship graph learning layer is employed to learn the relationships among technical charts generated by different indicators. Finally, by applying a GNN model combined with the relationship graphs of diverse technical charts, temporal patterns of stock indicator sequences are captured, fully utilizing the information between various technical charts to achieve accurate stock price predictions. Additionally, we further tested our framework with real-world stock data, showing superior performance over advanced baselines in predicting stock prices, achieving the highest net value in trading simulations. Our research results not only complement the existing applications of non-singular technical charts in deep learning but also offer backing for investment applications in financial market decision-making. Full article

The stochastic correlation for Brownian motions is the integrand in the formula of their quadratic covariation. The estimation of this stochastic process becomes available from the temporally localized correlation of latent price driving Brownian motions in stochastic volatility models for asset prices. By analyzing this process for Apple and Microsoft stock prices traded minute-wise, we give statistical evidence for the roughness of its paths. Moment scaling indicates fractal behavior, and both fractal dimensions (approx. 1.95) and Hurst exponent estimates (around 0.05) point to rough paths. We model this rough stochastic correlation by a suitably transformed fractional Ornstein–Uhlenbeck process and simulate artificial stock prices, which allows computing tail dependence and the Herding Behavior Index (HIX) as functions in time. The computed HIX is hardly variable in time (e.g., standard deviation of 0.003–0.006); on the contrary, tail dependence fluctuates more heavily (e.g., standard deviation approx. 0.04). This results in a higher correlation risk, i.e., more frequent sudden coincident appearance of extreme prices than a steady HIX value indicates. Full article

As a research objective in quantitative trading, the aim of portfolio management is to find the optimal allocation of funds by following the dynamic changes in stock prices. The principal issue with current portfolio management methods is their narrow focus on a single data source, neglecting the changes or news arising from sectors. Methods for integrating news data frequently face challenges with regard to quantifying text data and embedding them into portfolio models; this process often necessitates considerable manual labeling. To address these issues, we proposed a sector rotation portfolio management approach based on deep reinforcement learning (DRL) via multi-source information. The multi-source information includes the temporal data of sector and stock features, as well as news data. In terms of structure, in this method, a dual-layer reinforcement learning structure is deployed, comprising a multi-agent sector layer and a graph convolution layer. The former learns the trend of sectors, while the latter learns the connections between stocks in sectors, and the impact of news on sectors is integrated through large language models without manual labeling or fusing output information of other modules to provide the final portfolio management scheme. The results of simulation experiments on the Chinese and US (United States) stock markets show that our method demonstrates significant improvements over multiple state-of-the-art approaches. Full article

Expected Shortfall (ES) is a risk measure that is acquiring an increasingly relevant role in financial risk management. In contrast to Value-at-Risk (VaR), ES considers the severity of the potential losses and reflects the benefits of diversification. ES is often calculated using Historical Simulation (HS), i.e., using observed data without further processing into the formula for its calculation. This has advantages like being parameter-free and has been favored by some regulators. However, the usage of HS for calculating ES presents a potentially serious drawback: It strongly depends on the size of the sample of historical data, being typically reasonable sizes similar to the number of trading days in one year. Moreover, this relationship leads to systematic underestimation: the lower the sample size, the lower the ES tends to be. In this letter, we present examples of this phenomenon for representative stocks and bonds, illustrating how the values of the ES and their averages are affected by the number of chosen data points. In addition, we present a method to mitigate the errors in the ES due to a low sample size, which is suitable for both liquid and illiquid financial products. Our analysis is expected to provide financial practitioners with useful insights about the errors made using Historical Simulation in the calculation of the Expected Shortfall. This, together with the method that we propose to reduce the errors due to finite sample size, is expected to help avoid miscalculations of the actual risk of portfolios. Full article

Additive manufacturing and digital warehouses are transforming the way industries manage and maintain their spare parts inventory. Considering digital warehouses and on-demand manufacturing for spare parts during the project phase is a strategic decision that involves trade-offs depending on the operational needs and pricing structure. This paper aims to explore the spare part evaluation process considering both physical and digital warehouse inventories. A case asset is purposefully selected and four spare part management concepts are studied using a simulation modeling approach. The results highlight that the relevant digital warehouse scenario, used in this case, managed to completely reduce all emissions related to global spare parts supply; however, this was at the expense of reducing availability by 15.1%. However, the hybrid warehouse scenario managed to increase availability by 11.5% while completely reducing all emissions related to global spare parts supply. Depending on the demand rate, the digital warehousing may not be sufficient alone to keep the production availability at the highest levels; however, it is effective in reducing the stock amount, simplifying the inventory management, and making the supply process more green and resilient. A generic estimation model for spare parts engineers is provided to determine the optimal specifications of their spare parts supply and inventory while considering digital warehouses and on-demand manufacturing. Full article

Computational algorithms are systematically written instructions or steps used to solve logical and mathematical problems with computers. These algorithms are crucial to rapidly and efficiently analyzing complex data, especially in global optimization problems like portfolio investment optimization. Investment portfolios are created because investors seek high average returns from stocks and must also consider the risk of loss, which is measured using the value at risk (VaR). This study aims to develop a computational algorithm based on the metaheuristic particle swarm optimization (PSO) model, which can be used to solve global optimization problems in portfolio investment. The data used in the simulation of the developed computational algorithm consist of daily stock returns from the banking sector traded in the Indonesian capital market. The quantitative research methodology involves formulating an algorithm to solve the global optimization problem in portfolio investment with mathematical calculations and quantitative data analysis. The objective function is to maximize the mean-value-at-risk model for portfolio investment, with constraints on the capital allocation weights in each stock within the portfolio. The results of this study indicate that the adapted PSO algorithm successfully determines the optimal portfolio weight composition, calculates the expected return and VaR in the optimal portfolio, creates an efficient frontier surface graph, and establishes portfolio performance measures. Across 50 trials, the algorithm records an average expected return of 0.000737, a return standard deviation of 0.00934, a value at risk of 0.01463, and a Sharpe ratio of 0.0504. Further evaluation of the PSO algorithm’s performance shows high consistency in generating optimal portfolios with appropriate parameter selection. The novelty of this research lies in developing an accurate computational algorithm for determining the global optima of mean-value-at-risk portfolio investments, yielding precise, consistent results with relatively fast computation times. The contribution to users is an easy-to-use tool for computational analysis that can assist in decision-making for portfolio investment formation. Full article

Online courses in higher education became prevalent during the COVID-19 pandemic; however, their application requires technology to be fully integrated into the curriculum. This study explores the integration of a blockchain-based platform in a private online stock simulation trading course during the COVID-19 pandemic. Using a pre–post experimental design with 142 college students, it assessed learning behaviors and outcomes. Students collaborated with teaching assistants via LINE groups, fostering discussion and engagement. They received cryptocurrency rewards, which enhanced motivation and connected the course to their career goals. The findings suggest that combining blockchain and social networking is an effective approach to improving online education. This contributes to the literature on educational technology and online learning by exploring the integration of blockchain and social networking in higher education, specifically within the context of stock simulation trading courses, and demonstrates its impact on student motivation and learning outcomes. Full article

In the context of achieving the goal of carbon neutrality, exploring the changes in land demand and ecological carbon stocks under future scenarios at the urban level is important for optimizing regional ecosystem services and developing a land-use structure consistent with sustainable development strategies. We propose a framework of a coupled system dynamics (SD) model, patch generation land-use simulation (PLUS) model, and integrated valuation of ecosystem services and trade-offs (InVEST) model to dynamically simulate the spatial and temporal changes of land use and land-cover change (LUCC) and ecosystem carbon stocks under the NDS (natural development scenario), EPS (ecological protection scenario), RES (rapid expansion scenario), and HDS (high-quality development scenario) in Nanjing from 2020 to 2040. From 2005 to 2020, the expansion rate of construction land in Nanjing reached 50.76%, a large amount of ecological land shifted to construction land, and the ecological carbon stock declined dramatically. Compared with 2020, the ecosystem carbon stocks of the EPS and HDS increased by 2.4 × 10⁶ t and 1.5 × 10⁶ t, respectively, with a sizable ecological effect. It has been calculated that forest and cultivated land are the two largest carbon pools in Nanjing, and the conservation of both is decisive for the future carbon stock. It is necessary to focus on enhancing the carbon stock of forest ecosystems while designating differentiated carbon sink enhancement plans based on the characteristics of other land types. Fully realizing the carbon sink potential of each ecological functional area will help Nanjing achieve its carbon neutrality goal. The results of the study not only reveal the challenges of ecological conservation in Nanjing but also provide useful guidance for enhancing the carbon stock of urban terrestrial ecosystems and formulating land-use planning in line with sustainable development strategies. Full article

In the dynamic and uncertain stock market, precise forecasting and decision-making are crucial for profitability. Traditional deep neural networks (DNN) often struggle with capturing long-term dependencies and multi-scale features in complex financial time series data. To address these challenges, we introduce CMR-DQN, an innovative framework that integrates discrete wavelet transform (DWT) for multi-scale data analysis, temporal convolutional network (TCN) for extracting deep temporal features, and a GRU–LSTM–Attention mechanism to enhance the model’s focus and memory. Additionally, CMR-DQN employs the Rainbow DQN reinforcement learning strategy to learn optimal trading strategies in a simulated environment. CMR-DQN significantly improved the total return rate on six selected stocks, with increases ranging from 20.37% to 55.32%. It also demonstrated substantial improvements over the baseline model in terms of Sharpe ratio and maximum drawdown, indicating increased excess returns per unit of total risk and reduced investment risk. These results underscore the efficiency and effectiveness of CMR-DQN in handling multi-scale time series data and optimizing stock market decisions. Full article

The close relationship between land use and carbon stock is crucial for regional carbon balance, territorial and spatial planning, and the sustainable development of ecosystems. As a pioneer of Park Cities, Chengdu plays a vital role in Chinese cities. To investigate the impact of Park City construction on carbon stock, this study adopted a new perspective, the Park City perspective, using the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model to analyze the spatial and temporal differences in carbon stock. Additionally, we used Geographic Detector to analyze the driving factors of carbon stock in Chengdu. Based on the carbon peaking and carbon neutrality goals (peaking carbon dioxide emissions before 2030 and achieving carbon neutrality before 2060), we simulated the carbon stock in Chengdu for the years 2030 and 2060. Simultaneously, combining the Future Land Use Simulation (FLUS) model, we simulated the changing trends of carbon stock in Chengdu under three scenarios: the natural development scenario (NDS), cultivated land protection scenario (CLDS), and Park City scenario (PCS). The results show the following: (1) After the construction of the Park City, the quality of forest land improved, resulting in an increase in forest carbon stock by 1.19 × 10⁶ tons. (2) Compared to the scenario without Park City construction, the implementation of the Park City led to a total carbon stock increase of 3.75 × 10⁵ tons, with forest carbon stock increasing by 7.48 × 10⁵ tons. (3) The PCS is the most conducive to achieving the carbon peaking and carbon neutrality goals, with the highest carbon stock. (4) Carbon stock is mainly driven by socio-economic factors. Land use/land cover (LULC) has the greatest explanatory power, with a q value of 0.9. The Park City is of great significance for an increase in carbon stock in Chengdu. Full article

This paper leverages turbulence theory from physics to examine the similarities and differences between financial market volatility and turbulent phenomena on a statistical physics level. By drawing analogies between the dynamics of financial markets and fluid turbulence, an innovative analytical framework has been developed to enhance our understanding of the complexity inherent in financial markets. The research methodology involves a comparative analysis of several national stock market indices and simulated turbulent velocity time series, with a particular focus on key statistical properties such as probability distributions, correlation structures, and power spectral densities. Furthermore, a financial market capital flow model has been established, and corresponding solutions have been proposed. Through computational simulations and data analysis, it was discovered that financial market volatility shares some statistical characteristics with turbulence, yet there are significant differences in the shape of probability distributions and the timescales of correlations. This indicates that although financial markets exhibit patterns similar to turbulence, as a multivariate-driven complex system, their behavioral patterns do not completely correspond to natural turbulence phenomena, highlighting the limitations of directly applying turbulence theory to financial market analysis. Additionally, the study explores the use of Bézier curves to simulate market volatility and, based on these analyses, formulates trading strategies that demonstrate practical applications in risk management. This research provides fresh perspectives for the fields of financial market theory and econophysics, offering new insights into the complexity of financial markets and the prevention and management of financial risks. Full article

Intensive economic and human activities present challenges to the carbon storage capacity of terrestrial ecosystems, particularly in arid regions that are sensitive to climate change and ecologically fragile. Therefore, accurately estimating and simulating future changes in carbon stocks on the northern slope economic belt of Tianshan Mountains (NSEBTM) holds great significance for maintaining ecosystem stability, achieving high-quality development of the economic belt, and realizing the goal of “carbon neutrality” by 2050. This study examines the spatiotemporal evolution characteristics of the NSEBTM carbon stocks in arid regions from 1990 to 2050, utilizing a combination of multi-source data and integrating the Patch-generating Land use Simulation (PLUS) and Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) models. Additionally, an attribution analysis of carbon stock changes is conducted by leveraging land use data. The findings demonstrate that (1) the NSEBTM predominantly consists of underutilized land, accounting for more than 60% of the total land area in the NSEBTM. Unused land, grassland, and water bodies exhibit a declining trend over time, while other forms of land use demonstrate an increasing trend. (2) Grassland serves as the primary reservoir for carbon storage in the NSEBTM, with grassland degradation being the leading cause of carbon loss amounting to 102.35 t over the past three decades. (3) Under the ecological conservation scenario for 2050 compared to the natural development scenario, there was a net increase in carbon storage by 12.34 t; however, under the economic development scenario compared to the natural development scenario, there was a decrease in carbon storage by 25.88 t. By quantitatively evaluating the land use change in the NSEBTM and its impact on carbon storage in the past and projected for the next 30 years, this paper provides scientific references and precise data support for the territorial and spatial decision making of the NSEBTM, thereby facilitating the achievement of “carbon neutrality” goals. Full article

Land use serves as a connecting link between human activities and the natural ecology of the surface; under the multi-objective background of national policies and dual-carbon tasks, land use transformation is studied and simulated in multiple scenarios, and carbon stock changes are analyzed based on future land use to explore the path for a region to achieve multi-objective coordination. Drawing upon land use data from 2000 to 2020 in Lintao County, Gansu Province, we conducted an in-depth analysis of the dynamics governing land use transformation. Subsequently, employing the FLUS (Future Land Use Simulation) model, we simulated the projected land use for Lintao County in 2035 under various scenarios. Furthermore, we utilized the InVEST (Integrated Valuation of Ecosystem Services and Trade-offs) model to assess the change in carbon stock within the study area under each scenario. These analyses aim to furnish a robust scientific foundation for future land use planning endeavors in Lintao County. The conclusions are as follows: (1) The land use transition in Lintao County from 2000 to 2020 showed the strongest motivation for construction land growth, with continued rapid growth in the scale of urban land and other construction land and relatively slow growth in the land for rural settlement areas, while cropland and water areas continued to decrease, forest land grew slowly, the magnitude of land use change exhibited a higher intensity in river townships compared with mountainous townships. (2) The simulation results of cropland protection scenario (CPS), ecological protection scenario (EPS), economic development scenario (EDS), and comprehensive development scenario (CDS) in 2035 are better. Among them, the CDS, which considers various types of higher-level strategic requirements and can compensate for the single-goal nature of the single-demand scenario, demonstrates a higher level of rationality in the land use pattern. (3) The total carbon stock in descending order is the EPS, CDS, EDS, and CPS. Among these, the CDS is at a higher level of total carbon stock, and the changes in carbon stock in each land use site are more balanced, which is an ideal carbon stock state and a scenario more in line with multi-objective coordination. Full article

This paper introduces a novel deep learning approach for intraday stock price direction prediction, motivated by the need for more accurate models to enable profitable algorithmic trading. The key problems addressed are effectively modelling complex limit order book (LOB) and order flow (OF) microstructure data and improving prediction accuracy over current state-of-the-art models. The proposed deep learning model, TrioFlow Fusion of Convolutional Layers and Gated Recurrent Units (TFF-CL-GRU), takes LOB and OF features as input and consists of convolutional layers splitting into three channels before rejoining into a Gated Recurrent Unit. Key innovations include a tailored input representation incorporating LOB and OF features across recent timestamps, a hierarchical feature-learning architecture leveraging convolutional and recurrent layers, and a model design specifically optimised for LOB and OF data. Experiments utilise a new dataset (MICEX LOB OF) with over 1.5 million LOB and OF records and the existing LOBSTER dataset. Comparative evaluation against the state-of-the-art models demonstrates significant performance improvements with the TFF-CL-GRU approach. Through simulated trading experiments, the model also demonstrates practical applicability, yielding positive returns when used for trade signals. This work contributes a new dataset, performance improvements for microstructure-based price prediction, and insights into effectively applying deep learning to financial time-series data. The results highlight the viability of data-driven deep learning techniques in algorithmic trading systems. Full article

This paper presents an in-depth analysis of the impact of forest carbon sink trading in China, examining its effects from 2018 to 2030 under various carbon pricing scenarios. Using the Global Timber Market Model (GFPM) along with the IPCC Carbon Sink Model, we simulate the potential shifts in China’s forest resources and the global timber market. The study finds that forest carbon trading markedly boosts China’s forest stock and carbon sequestration, aligning with its dual carbon objectives. China’s implementation of forest carbon trading is likely to result in a degree of carbon leakage on a global scale. During the forecast period, our study reveals that the carbon leakage rates under three different forest carbon trading price scenarios, which at estimated at 81.5% (USD 9.8/ton), 64.0% (USD 25/ton), and 57.8% (USD 54/ton), respectively. Notably, the leakage rate diminishes as the forest carbon sink price increases. Furthermore, analysis also suggests that regional variations in the average carbon sequestration capacity of forests, alongside the structure of China’s timber imports, emerge as significant factors influencing the extent of carbon leakage. Full article