Real-time Trading Research Articles

Enhancing Carbon Trading Mechanisms through Innovative Collaboration: Case Studies from Developing Nations

Against a backdrop of global climate change mitigation efforts, carbon trading has emerged as a critical mechanism, yet developing countries often lack the necessary infrastructure and collaborative frameworks. The research investigates how intermediaries facilitate stakeholders and employ innovative practices to foster effective carbon trading markets. Methodologically, it employs a qualitative approach, conducting in-depth case studies of four intermediaries through 32 semi-structured interviews and archival document. Findings underscore the pivotal role of digital platforms in enabling real-time trading, rigorous standardization processes to ensure market credibility, and multi-stakeholder engagement strategies that promote inclusive participation. This research contributes to the theoretical understanding of carbon trading by illustrating how digital platforms and technological integration enhance resource acquisition and allocation. It emphasizes the significance of standardization and verification processes in building trust among stakeholders, crucial for effective supply chain collaboration. Practically, the study highlights the benefits of these approaches in enhancing market efficiency and transparency. It also underscores the importance of multi-stakeholder engagement strategies and strategic alliances for creating resilient and inclusive carbon trading markets, offering actionable insights for stakeholders and policymakers alike.

Siamese Graph Convolutional Split-Attention Network with NLP based Social Sentimental Data for enhanced stock price predictions

Predicting stock market behavior using sentiment analysis has become increasingly popular, as customer responses on platforms like Twitter can influence market trends. However, most existing sentiment-based models struggle with two major issues: inaccuracy and high complexity. These problems lead to frequent prediction errors and make the models difficult to implement in real-time trading systems. To address these challenges, this paper proposes a new method called Siagra-ConSA-HSOA (Siamese Graph Convolutional Split-Attention Network with NLP-based Social Sentiment Data). Two data sources feed the model: specifically, NIFTY-50 Stock Market and real-time Twitter sentiment. Through Natural Language Processing (NLP), the raw data is pre-processed and key features are extracted before they are fused into a unified dataset using a cross-domain transformer, namely CDSFT, and then Circle-Inspired Optimization Algorithm (CIOA) selects the most important features from this dataset. This decreases the complexity of the model without losing essential information. Finally, a Graph Convolutional Split-Attention Network (SGCSAN) for promisingly predicting whether the stock prices are going to hit the ground and fly high again or is going to nosedive with Humboldt Squid Optimization Algorithm (HSOA) is introduced to further improve accuracy with lesser error generation. The proposed model Siagra-ConSA-HSOA achieved 99.9% accuracy and 99.8% recall in the testing stage, meaning that such a model performs better than the current approaches both in prediction accuracy and efficiency. Thus, this is a glimmer that the model shall be able to overcome some of the main problems with the current techniques used in predicting the behavior of the stock market.GitHub Repository: https://github.com/jramans2/Siamese-GCN-SplitAttention-Stock-Prediction.git

Quantum-Inspired AI for Optimized High-Frequency Trading

This article explores the transformative role of quantum-inspired AI in optimizing financial practices, particularly within high-frequency trading (HFT) in the financial sector. As HFT operates in an environment of rapid transactions and significant market volatility, the need for advanced optimization techniques becomes paramount. Quantum-inspired algorithms leverage principles from quantum mechanics, such as superposition and tunneling, to enhance various aspects of trading strategies. These algorithms enable rapid optimization of asset allocation, real-time trade execution, and proactive fraud detection, effectively addressing the challenges posed by traditional financial models. By facilitating simultaneous evaluation of multiple strategies and enabling real-time analysis of complex trading patterns, quantum-inspired AI significantly improves decision-making speed and accuracy. The financial implications of this advancement are profound, leading to higher profitability, improved market integrity, and enhanced trust among market participants. Ultimately, integrating quantum-inspired AI in finance represents a crucial step towards harnessing cutting-edge technology to reshape trading dynamics, paving the way for innovative strategies that can adapt to the evolving landscape of financial markets. This study underscores the potential of quantum-inspired AI to redefine operational efficiency in finance, ensuring competitiveness in an increasingly complex trading environment.

An efficient hybrid approach for forecasting real-time stock market indices

The stock market’s volatility, noise, and information overload necessitate efficient prediction methods. Forecasting index prices in this environment is complex due to the non-linear and non-stationary nature of time series data generated from the stock market. Machine learning and deep learning have emerged as powerful tools for identifying financial data patterns and generating predictions based on historical trends. However, updating these models in real-time is crucial for accurate predictions. Deep learning models require extensive computational resources and careful hyperparameter optimization, while incremental learning models struggle to balance stability and adaptability. This paper proposes a novel hybrid bidirectional-LSTM (H.BLSTM) model that combines incremental learning and deep learning techniques for real-time index price prediction, addressing these scalability and memory challenges. The method utilizes both univariate time series derived from historical index prices and multivariate time series incorporating technical indicators. Implementation within a real-time trading system demonstrates the method’s effectiveness in achieving more accurate price forecasts for major stock indices globally through extensive experimentation. The proposed model achieved an average mean absolute percentage error of 0.001 across nine stock indices, significantly outperforming traditional models. It has an average forecasting delay of 2 s, making it suitable for real-time trading applications.

Study On Operation Strategy Of CSP Peak-Regulating Power Station Based On Spot Trading Market In Gansu Province

On March 3, 2022, the National Development and Reform Commission of China and the National Energy Administration of China jointly published the Notice on Accelerating the Construction of the Electricity Spot Market. The notice indicated that the government would support the uninterrupted operation of the power spot pilot project with conditions and form a long-term and stable electricity spot market as soon as possible. These steps will help rapidly improve China's electricity spot market construction. Due to its large-scale energy storage capacity, the Concentrated Solar Power (CSP) station can be used as a peak-regulating power station to provide grid-friendly long-term peak regulating capacity and moment of inertia for the power system. When CSP stations participate in electricity spot market trading, they can optimize their operation strategy to generate more electricity during periods with higher electricity prices, thereby obtaining more profits. In this paper, a 100MW CSP Peak-Regulating Station with an 80.0hm2 reflecting area of Heliostats Field (HF) is designed in Gansu, China. In the Peak-Regulating operation strategy, the most suitable TES Capacity for this project is determined to be 15h. We take this CSP station as the research objective to optimize the operation strategy of the power station. The research results indicate that optimizing the operation strategy will increase the power station's annual electricity sales revenue by about 19.97% before the strategy was optimized when the power station participated in the real-time trading of the Gansu electricity spot market in 2022.

Real time aggregation control of P2H loads in a virtual power plant based on a multi-period stackelberg game

Power to Heat (P2H) technology is seen as an effective solution for integrating stochastic wind power. Particularly in real-time electricity markets, high-precision wind power forecasts enable the load to better accommodate its fluctuations. Nonetheless, the shorter time scales of real-time trading pose challenges for efficiently aggregating a large, heterogeneous, and dispersed loads and fully harnessing the thermal storage capabilities of loads to follow wind power fluctuations across multiple periods. Against this backdrop, this paper proposes an aggregation control approach for P2H loads with considering multi-period Stackelberg game strategy within the framework of a load-oriented virtual power plant (VPP). For multi-period real-time trading, a Stackelberg game model based on a dynamic price ceiling is established with considering dynamic supply-demand balance between wind power and P2H loads; To enhance load aggregation effectiveness, a dynamically updated temperature-power aggregation model is developed by employing model order reduction, variables continuousization, and linear superposition on second-order equivalent thermodynamic model; To improve load decomposition efficiency, a hierarchical and multi-step control strategy encompassing the continuousization of discrete variables is utilized to simplify the problem. Finally, a simulation example is presented using actual data from a power grid in northern China to validate the effectiveness of the proposed method.

Влияние злоупотребления доминирующим положением на объединенных внутрисуточных рынках электроэнергии ЕС на интеграцию возобновляемых источников энергии (ВИЭ)

The article is devoted to a problem of the abuse of dominance in the EU coupled intraday electricity markets and the consequences of such abuse for the integration of RES generation. The relevance of the study is due to the increased interest in the role of competition policy in achieving sustainable development goals. The problem under consideration is revealed by an example of an investigation by the UK Office of Gas and Electricity Markets (Ofgem) into EPEX electricity exchange about the abuse of dominance at coupled intraday auctions between Ireland and the UK. The following results were obtained in the study. Firstly, it is established that the abuse of dominance in coupled intraday electricity markets may manifest itself in access denial by the essential facility owner (EPEX) for its competitors (Nord Pool power exchange) to the necessary infrastructure for coupled intraday auctions (shared order book). Secondly, it is proven that the coupled intraday electricity market is an important mechanism for integrating RES generation into the energy system due to the possibility of real-time trading and optimization of cross-border capacity allocation between coupled markets. Thirdly, it is revealed that access denial for competitors to the shared order book for coupled intraday auctions reduces the liquidity of the considered market due to the cut-off of some bidders. It is shown that reduced liquidity of the intraday electricity market hinders elimination of imbalances in the energy system arising from the volatility of power generation from RES. Therefore, it is concluded that the violation of competition in the coupled intraday electricity markets via abuse of dominance can hinder the cost-effective integration of RES generation and greening of the power industry.

A FAST Hardware Decoder Optimized for Template Features to Obtain Order Book Data in Low Latency

High-Frequency Trading (HFT) systems require high computational performance for real-time trading and data analysis. FAST protocol, an extension of FIX protocol, is one of the main communication pattern adopted by these systems. This work presents an open source hardware component, implemented in Field-Programmable Gate Array (FPGA), to decode market data messages to produce the necessary commands to construct order books in low latency for the Brasil Bolsa Balcão B3 stock exchange. The proposed hardware component optimized for a B3 template is able to decode messages at average latency of 0.72us and throughput of 1.4M FAST messages per second. The results are from logs of real messages with average size of 85 bytes each.

H3O-LGBM: hybrid Harris hawk optimization based light gradient boosting machine model for real-time trading.

The gross domestic product (GDP) of a country is mainly dependent on its trade and external sector which improves the country's income. According to FY2021-2022, India's nominal GDP is estimated to be 3.12 trillion US dollars. Overall exports and imports have a year-over-year increase of 49.6% and 68% respectively. Machine learning techniques have the potential to improve India's Current gross value by up to 15% by the year 2035. The integration of data, Technology, and talent helps to create intelligent models that enhance artificial intelligence growth. This paper presents an optimized light gradient boosting machine (Light GBM) model using the hybrid Harris hawk optimization (H3O) algorithm for trade forecasting. The overfitting problem in the conventional Harris Hawk Optimization is overcome using the exclusive feature bundling (EFB) and the gradient-based one-side sampling (GOSS) methodologies. The H3O optimization algorithm offers fast convergence by optimizing different lightGBM parameters such as a number of training iterations, maximum depth, minimal data in the leaf, etc. To improve the performance, one step further, the residual errors of the optimized lightGBM model are corrected using the Markov Chain model. The main aim of the optimized lightGBM model is to extract the crucial input values of certain variables such as imports and exports of goods and services, service trade, and merchandise trade and predict the price movement decision. The proposed model identifies the interrelationship with the external market and future market growth along with analyzing the variation in market conditions. The prediction decision is mainly to hold, but, or sell the stocks. When evaluated using the precious metal price forecast and stock market datasets, the proposed methodology shows that the hybrid approach can enhance the prediction performance. The results show that the input parameters were efficient in predicting the economic growth regarding the Intermarket trading system (ITS) and services with higher accuracy.

Reinforcement Learning for Stock Prediction and High-Frequency Trading With T+1 Rules

The high-frequency trading framework for the price trend prediction model and trading strategy has been a popular approach for T+0 trading in the stock market. The prediction model is used to predict price trends, and the trading strategy is used to determine the price and volume of the order. Most trading strategies consist of multiple trading logic associated with certain tuning parameters. These parameters significantly affect the profitability of high-frequency trading frameworks. There are two main disadvantages of this framework: 1) the price trend prediction model can not adapt to the current market data distribution, and 2) the trading strategy can not adapt to the current market conditions automatically. Thus, the framework cannot always maintain positive revenue. To address this problem, we propose a novel dynamic parameter optimization algorithm based on reinforcement learning for stock prediction and trading, and to generate an adaptive trading framework. First, we use a rolling model training method for stock price trend prediction. Second, we regard each set of strategy parameters as action and devise an inverse reinforcement learning algorithm for the reward function to accurately estimate the reward of each action. Because of the T+1 trading rules of the Chinese stock market, we consider the constraint of limited short position in the reward function. Finally, a reward-enhanced upper confidence bound (UCB) selection algorithm is proposed to automatically optimize the parameters of the trading logic in real-time trading. The experimental results show that our method achieves competitive performance in the Chinese stock market.

Real-Time Trading System Based on Selections of Potentially Profitable, Uncorrelated, and Balanced Stocks by NP-Hard Combinatorial Optimization

Real-Time Trading System Based on Selections of Potentially Profitable, Uncorrelated, and Balanced Stocks by NP-Hard Combinatorial Optimization

Navigating Financial Complexity: Language Processing Insights for Modern Businesses

Complex financial markets generate massive volumes of unstructured text data from news, publications, social media, and analyst comments. NLP can assist investors and traders make real-time judgments using this data. Analysis of markets This article reviews NLP advancements in three main areas. Generally favorable, negative, or neutral opinions toward companies, industries, or markets. Conversational tone predicts market and investor confidence using machine learning and sentiment lexicons. Finance conversation topic discovery. NLP algorithms may find hidden patterns and investment possibilities by identifying frequently occurring keywords, phrases, and entities in vast text corpora. Classifying critical events like profits, mergers, and regulations. NLP canwarn traders and improve real-time trading decisions by gathering vital news and financial data.Sentiment analysis and transaction volume are used in stock market case studies. Market mood may affect trading performance, since numerical models link favorable sentiment to stock price increases. The importance of active trading in price changes is shown by regular trade volumes

Optimization-based economic analysis of energy storage technologies in a coupled electricity and natural gas market

This work presents a stochastic mixed-integer linear programming (MILP) optimization framework to investigate the optimal participation and economics of various energy storage technologies, such as pumped-hydro, advanced adiabatic and diabatic compressed air systems and li-ion battery, in a perfectly competitive coupled electricity and natural gas market. The clearing scheme pertains to energy-only markets, aiming to optimize dispatch and maximize social welfare for the integrated energy system, through a two-stage stochastic programming. The first stage presents the day-ahead market clearing procedure, while the second stage illustrates the integrated system operation in the real-time trading floor, through a set of plausible wind power generation realizations. The two markets mainly interact the bilateral operation of the diabatic compressed air energy storage system, both as an electricity producer and as natural gas consumer. The proposed algorithm is applied to a modified IEEE 24-bus power grid and a single-node gas network and provides a thorough analysis of the operational characteristics and profitability of each energy storage technology in the integrated energy system. Results illustrate that electricity storage systems can increase their overall profits under power transmission congestion and while wind power generation volatility increases from 5 % up to 52 %. In contrast, a decrease by 3.1 % in the social welfare is realized in the case of power congestion while this figure is approximately 2.54 % under wind power volatility increase.

Mitigation of the Inefficiency in Imbalance Settlement Designs Using Day-Ahead Prices

The design of electricity imbalance pricing mechanisms is internationally controversial. Policies on whether to permit virtual trading for market participants and whether, or how, to impose penalty incentives on the imbalance volumes vary widely. Furthermore, market designs vary depending whether the imbalance prices are obtained directly from real-time trading or based upon the offer and demand functions from the day-ahead energy markets. This paper develops an analytical framework for evaluating designs for imbalance settlement mechanisms and we have selected the Japanese electricity market, which has undergone several revisions in its imbalance mechanism, as a good example to assess such variations. We develop a predictive approach for the imbalance volumes and price densities using two-step quantile regressions and derive a new trading optimization for a virtual trader's arbitrage position. We construct supporting models to estimate prediction errors for renewable power and demand as drivers of imbalance volume. The empirical analysis reveals that even in a mechanism with imbalance penalties based upon day-ahead reference prices, virtual trading may still be beneficial to market participants as well as to the system operator. We also find that greater market transparency is crucial for increased benefits. The insights generalize beyond the Japan case study.

Digital Transformation in the Stockbroking Industry and its Role in Strong Retail Investor Participation in the Indian Stock Market

The Indian stock market is experiencing a dramatic change in its investor participation structure by way of increased involvement of retail investors, especially after the introduction of various technology-backed mobile investment apps. The digital transformation in the stockbroking industry paved the way for attracting more retail investors through their investment apps, reduced investment costs like commission, Demat charges, and developments in the digital payment modes in India. The total Demat account holders of CDSL and NSDL combined crossed over 90 million as of 31st March 2022. The introduction of the concept of technology-backed discount stockbroking accelerated the competition in the stockbroking industry thereby compelling the traditional full-service brokers to switch from their outdated telephone-based trading arrangement to technology-backed trading arrangements for their investors. The real-time trading opportunities by monitoring the real-time price movements of securities helped retail investors to build their investment portfolios. Even though the digital transformation in the stockbroking industry is attracting more retail investors, retail participation in the Indian stock market is still very low compared to other developed and developing economies. By overcoming the various challenges that restrict individuals from investing in securities, the Indian stock market can experience a further increase in the overall retail investor participation. Drifting the savings of retail investors to the stock market instruments will strengthen the cashflows in the stock market.

Gambling and online trading: emerging risks of real-time stock and cryptocurrency trading platforms

ObjectivesOnline platforms enable real-time trading activities that are similar to those of gambling. This study aimed to investigate the associations of traditional investing, real-time stock trading, and cryptocurrency trading with excessive behavior and mental health problems. Study designThis was a cross-sectional population-based survey. MethodsThe participants were Finnish people aged 18–75 years (N = 1530, 50.33% male). Survey asked about monthly regular investing, real-time stock-trading platform use, and cryptocurrency trading. The study had measures for excessive behavior: gambling (Problem Gambling Severity Index), gaming (Internet Gaming Disorder Test), internet use (Compulsive Internet Use Scale), and alcohol use (Alcohol Use Disorders Identification Test). Psychological distress (Mental Health Inventory), perceived stress (Perceived Stress Scale), COVID-19 anxiety, and perceived loneliness were also measured. Background factors included sociodemographic variables, instant loan taking, and involvement in social media identity bubbles (Identity Bubble Reinforcement Scale). Multivariate analyses were conducted with regression analysis. ResultsWithin the sample, 22.29% were categorized into monthly regular investors only, 3.01% were investors using real-time stock-trading platforms, and 3.59% were cryptomarket traders. Real-time stock-trading platform use and cryptocurrency trading were associated with younger age and male gender. Cryptomarket traders were more likely to have an immigrant background and have taken instant loans. Both real-time stock-trading platform use and cryptomarket trading were associated with higher excessive behavior. Cryptomarket traders especially reported higher excessive gambling, gaming, and internet use than others. Cryptomarket traders reported also higher psychological distress, perceived stress, and loneliness. ConclusionsRegular investing is not a risk factor for excessive behavior. However, rapid online trading platforms and applications were significantly more commonly used by participants reporting excessive behavior and mental health problems. The strong association between cryptomarket trading and excessive behavior in particular underlines the need to acknowledge the potential risks related to real-time trading platforms.

Auto uning of price prediction models for high-frequency trading via reinforcement learning

In this paper, we propose an online model optimization algorithm based on reinforcement learning for quantitative trading. The combination of prediction model and trading policy is the most commonly used framework in practical quantitative trading. Integrated with machine learning methods, this framework brings huge profits to quantified companies. In the framework, the prediction model is used to predict future trading price trend, and the trading policy is used to determine the price and number of orders. Even though, the shortcomings of machine learning models are obvious, mainly are, (1) Slow prediction speed. Huge human-craft features and model computing cost much time, which is ten times of pure trading policy without model. (2) Poor generalization. This kind of models can hardly adapt to market data in each period, because market traders will change time to time at micro level, thus the distribution of market data will change. But current model is trained on a long period dataset, it achieves best effect at average, but can not adapt to different market at each period. To address this problem, we propose a novel online model optimization algorithm. A light model library will be constructed. Each light model in this library corresponds to a different market distribution. By devising the appropriate reward function via inverse reinforcement learning algorithm, the algorithm can accurately estimate the profits of each model. Then the model can be selected automatically in real-time trading, so that the trading policies can automatically adapt to changes in trading market, overcoming previous shortcoming of manually updating model and slow prediction speed. Experimental results show that the proposed algorithm achieves state-of-the-art performance on China Commodity Futures Market Data.

The interaction between volatility and high frequency trading

In this study, we explore the linkage between high frequency trading activity and market volatility. Though the findings of existing studies for this topic until now are rather inconclusive, they agree with the impact HFT exert to volatility. In our design, we take advantage of the trading activity to predict real time trading. We use the VIXY which is an ETF of VIX and focuses on short term performance, finding that the ask side of high frequency trading activities has far more significant predictability for both the level of VIXY and return of VIXY, while the bid side seems to be trivial.

Design and Comparative Analysis on Real-Time Trade of Road Priority in Connected Traffic

New technologies present opportunities to re-think the real-time traffic operation. Trade of road priority using schemes such as auctions, credits, and direct-transactions, provides a novel way to better serve heterogeneous traffic demands in the future connected environment. Implementations of these schemes come with a common phenomenon called the network effect, meaning that the value of the scheme depends heavily on the percentage of travelers that subscribe to this scheme. To encourage travelers to be subscribers, the traffic operator needs to reasonably consider the treatments for both subscribers and outsiders, and have the knowledge of each scheme’s impact on individuals and society. Only in this way can the government choose an appropriate scheme that will be accepted by the public. However, most existing studies simply assumed a 100% of subscribers and ignored the travelers’ autonomy and smartness in choice behavior. Such neglect may easily render the economic schemes failed in practice due to public resistance or loss in subscribers. To fill up this research gap, this paper designs treatments to both subscribers and outsiders for different schemes in intersection operations. We investigate travelers’ choice behaviors under different scenarios, and make comparative analysis about individual benefits, social benefit, and social equity between different schemes. The findings of this paper can support the government’s decision on the system design of road priority trading.

Downside risk and the performance of volatility-managed portfolios

Recent studies find mixed evidence on the performance of volatility-managed portfolios. We show that strategies scaled by downside volatility exhibit significantly better performance than strategies scaled by total volatility. The improved performance is evident in spanning regressions, direct Sharpe-ratio comparisons, and real-time trading strategies. A decomposition analysis indicates that the enhanced performance of downside volatility-managed portfolios is primarily due to return timing, i.e., downside volatility negatively predicts future returns. We find that employing fixed-weight strategies significantly improves the performance of volatility-managed portfolios for real-time investors. Our results hold for nine equity factors and a broad sample of 94 anomaly portfolios.