Profitable Trading Research Articles

PreBit — A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin

Bitcoin, with its ever-growing popularity, has demonstrated extreme price volatility since its origin. Extreme price fluctuations have been known to occur due to tweets from Elon Musk, Michael Saylor, and others. In this paper, we aim to investigate whether we can leverage Twitter data to predict these extreme price movements. Existing social media models often take a shortcut and include sentiment extracted from tweets. In this work, however, we want to embed the actual tweets in a domain-informed way, and investigate whether they have an impact. Hence, we propose a multimodal deep learning model for predicting extreme price fluctuations that takes as input candlestick data, prices of a variety of correlated assets, technical indicators, as well as Twitter content. To train the model, a new dataset of 5,000 tweets per day containing the keyword ‘Bitcoin’ was collected from 2015 to 2021. This dataset, called PreBit, is made available online11https://www.kaggle.com/datasets/zyz5557585/prebit-multimodal-dataset-for-bitcoin-price., as is our model.22https://github.com/AMAAI-Lab/PreBit. Our proposed hybrid multimodal model consists of an SVM model based on price data, which is fused with a text-based Convolutional Neural Network. In the text-based model, we use the sentence-level FinBERT embeddings, pretrained on financial lexicons, so as to capture the full contents of the tweets and feed it to the model in an understandable way. In an ablation study, we explore whether adding social media data from the general public on Bitcoin improves the model’s ability to predict extreme price movements. Finally, we propose and backtest a trading strategy based on the predictions of our models with varying prediction threshold and show that it can be used to build a profitable trading strategy with a reduced risk over a ‘hold’ or moving average strategy.

Short-Term Cryptocurrency Price Fluctuation Prediction Framework Using Machine Learning

Abstract: Our project aim is to predict the future price of the bitcoin using machine learning algorithms. In the modern world cryptocurrency is become more trendy and reaches the youngsters to invest in the stock market and to generate some profitable trades. To invest their money in cryptocurrency we are just helping the investors like peoples and also involving the organization to invest in the bitcoin and to make good profitable trades. Initially it utilizes the historical data to predict the future price of the bitcoin. It involves considering factors such as market sentiment, news and events ,technical analysis, and global economic trends. Different machine learning algorithms are applied on the a data and the accuracy is compared to see which algorithm performed better. It includes the performance metrics like precision, recall scores are also taken into consideration for evaluating the model In cryptocurrency market it contains 'n' number of coins .Among those coins we can take any coin to predict the future price which will able to help the investors who are all investing their money in cryptocurrency market.

THE INFLUENCE OF MACRO VARIABLES ON FOREIGN DIRECT INVESTMENT (FDI) IN 8 ASEAN COUNTRIES

The title of the research is The Effect of Macro Variables on Foreign Direct Investment (FDI) in 8 Asean Countries. Tujaun research is to determine the influence of macro variables on foreign direct investment (FDI) in 8 Asean countries. The method of analysis in this study is quantitative method and uses secondary data from the World Bank. The data used consists of time series and cross-section data, so the panel data analysis method is used to analyse it. Panel data consists of space and time dimensions, combining the characteristics of cross-section data with time series data. Time series data was obtained from 2005-2022 with cross-section data on 8 ASEAN member countries, namely Indonesia, Malaysia, Singapore, Thailand, the Philippines, Brunei Darussalam, Vietnam, and Cambodia. The data analysis method used is quantitative analysis using panel data regression. This study uses panel data regression to determine differences between individuals or in each ASEAN country. The results showed that Foreign Direct Investment (FDI) is the flow of capital from abroad. FDI occurs when companies from one country invest directly in another country. FDI plays an important role in promoting economic growth, technology transfer, job creation, and productivity improvement in recipient countries. The decision to make foreign investment can be influenced by several macro variables, such as GDP, inflation, exchange rate, trade level, and labour force. This study uses panel data analysis method with data from 8 ASEAN countries in 2005-2022. The results of the study show that GDP and labour force have a positive effect on FDI in 8 ASEAN countries. Meanwhile, inflation, exchange rate, and trade profitability variables have no effect on FDI.

KEWENANGAN PEMERINTAH DAERAH KOTA PEKANBARU TERHADAP PELAKSANAAN PEMBINAAN PASAR SUKARAMAI TRADE CENTER

Regional Goverments manage and manage their regions inthe hope of creating community welfare in their respective areas, one of which is the policy made by local goverments to improve the welfare of the people in the area, namely by Implementing Market Arrangement Authority in Pekanbaru City. The agency authorized and responsible for managing the people’s market is the market office. The Pekanbaru City Goverments, especially the Market Service, must be able and obliged and always strive for the People’s Market (including the Main Market and Supporting Market) to become an effective and profitable trading facility for the lower middle class community. For this reason, People’s Market should get support from the Pekanbaru City Goverments, both in the form of revitalization (market rejuvenation) and the daily management of the People’s Market in the form of structuring, empowering, fostering and monitoring that is carried out strictly. The purpose of writing this thesis, namely: First, to find out the implementation of the Regional Regulation Number 9 of 2014 conceming the Management of the People’s Market. Shopping Centers and Supermarkets in Pekanbaru City. Second. To find out the inhibiting factors that affect the Regional Government in the Pekanbaru Market Arrangement. This type of research is sociological legal research, where research wants to see the correlation between law and society, so as to be able to reveal the effectiveness of law enforcement in society and identify unwritten laws that apply to people in the field or to society. The data sources used were primary data and secondary data consisting of primary legal materials, secondary legal materials, and tertiary legal materials. The data collection techniques in this study were observation, interview, and literature review. After the data was collected, it was analyzed to draw conclusions. From the results of the study, it was concluded that, First, the implementation of Sukaramai Trade Center Market Development Based on Article 34 paragraph (2) letter C of Pekanbaru City Regional Regulation Number 9 of 2014 has not been carried out optimally by the government. Second, the inhibiting factors that influence the Regional Government in the Implementation of Pekanbaru Market Development are the legal factor itself, official staff factors, and unclear regulatory factors. Suggestions from the author, namely, the Pekanbaru City STC Market and Market Management Office pay more attention to the rights of traders in accordance with Regional Regulations Article 34 paragraph (2) letter C Number 9 of 2014

Stock Price Prediction Using Stacked LSTM

Abstract: In this project we attempt to implement machine learning approach to predict stock prices. Machine learning is effectively implemented in forecasting stock prices. The objective is to predict the stock prices in order to make more informed and accurate investment decisions. We propose a stock price prediction system that integrates mathematical functions, machine learning, and other external factors for the purpose of achieving better stock prediction accuracy and issuing profitable trades. There are two types of stock trading. You may know of intraday trading by the commonly used term "day trading." Intraday traders hold securities positions from at least one day to the next and often for several days to weeks or months. LSTMs are very powerful in sequence prediction problems because they’re able to store past information. This is important in our case because the previous price of a stock is crucial in predicting its future price. While predicting the actual price of a stock is an uphill climb, we can build a model that will predict whether the price will go up or down for next 30 days

Profitability of insider trading in Turkey

This study presents the first comprehensive evidence of insider trading patterns and abnormal profits in the Turkish stock market using almost 65,000 insider transactions for the period of 2008–2019. Our findings show that insiders earn a significant 6.58% abnormal profit during the one year following insider trading. Officers, directors, and institutional investors earn even more. Both purchases and sales are profitable. Top executives, major shareholders, and institutional investors earn significant dollar profits. Additionally, uninformed investors can beat the market by mimicking the portfolios of insiders, while evidence shows that regulatory changes do not reduce insiders’ profits. Finally, this study provides important trading implications for investors and regulatory implications for policymakers everywhere.

Influence of Net Working Capital on Trade Profitability in Serbia

The problem of managing working capital, i.e. net working capital in trade, is very specific, challenging, current, significant and complex. In order to achieve the target financial performance, it is necessary to manage working capital as efficiently as possible. Based on that, this paper analyses the dynamics of size and the impact of net working capital on the profitability of trade in Serbia. In the period 2013 - 2021, in the trade of Serbia, the maximum amount of net working capital was achieved in 2021, the maximum percentage of net working capital from assets was achieved in 2021, the maximum percentage of net working capital from sales was achieved in 2021, and the maximum profitability was achieved in 2021. In the specific case, there is a strong correlation between profitability and net working capital of trade in Serbia. The coefficient of determination is high (Adjusted R Square .941; Sig. F Change .000). The influence of net working capital on the profitability of trade in Serbia is very significant (Sig. .000). This means, in other words, that more efficient management of net working capital can have a significant impact on the profitability of trade in Serbia. Observed dynamically, the amount of net working capital of trade in Serbia has increased recently. This had a positive impact on its liquidity, solvency, efficiency and profitability. Recently, the productivity of trade in Serbia has also increased. The factors that influenced it were: favourable economic climate, foreign retail chains, application of new business models, new concepts of management of costs, income, profit, customers, product categories, application of the concept of sustainable development and digitization of the entire business.

Social networks and managerial rent‐seeking: Evidence from executive trading profitability

AbstractThis study examines whether board social networks are associated with executive trading profitability. Using a sample of US public firms with a history of executive trading from years 2000 to 2015, we find robust evidence that the profitability of executive trading is significantly lower in firms with higher levels of board social networks. The evidence is consistent with our view that board social networks effectively curb executives' private information advantage over outsiders, thus leading to a lower level of managerial rent‐seeking. Our research has policy implications for regulators concerned about the role of corporate board in capital markets.

Does Social Capital Mitigate Managerial Self-Dealing? Evidence From Insider Trading

In this study, we examine whether the social capital surrounding the firm’s corporate headquarters mitigates managerial self-dealing in the form of opportunistic insider trading. We find strong evidence that the level of social capital in the region surrounding the firm’s headquarters is negatively and significantly associated with insider trading profitability. We also find that the negative association between social capital and insider trading profitability is more pronounced when governance is weaker and corporate opacity is higher, instances where insiders have greater opportunities to trade on their private information. Further analyses on the potential mechanisms suggest that the negative association is stronger when the firm’s social networks are denser and when the civic norms in the region are stronger. Overall, our article contributes to the growing social capital literature in accounting and finance by providing direct empirical evidence that social capital mitigates managerial self-serving behavior in the form of opportunistic insider trading.

Clean Energy Action Index Efficiency: An Analysis in Global Uncertainty Contexts

Climate change, the scarcity of fossil fuels, advances in clean energy, and volatility of crude oil prices have led to the recognition of clean energy as a viable alternative to dirty energy. This paper investigates the multifractal scaling behavior and efficiency of green finance markets, as well as traditional markets such as gold, crude oil, and natural gas between 1 January 2018, and 9 March 2023. To test the serial dependency (autocorrelation) and the efficient market hypothesis, in its weak form, we employed the Lo and Mackinlay test and the DFA method. The empirical findings showed that returns data series exhibit signs of (in)efficiency. Additionally, there is a negative autocorrelation among the crude oil market, the Clean Energy Fuels Index, the Global Clean Energy Index, the gold market, and the natural gas market. Arbitration strategies can be used to obtain abnormal returns, but caution should be exercised as prices may increase above their actual market value and reduce the profitability of trading. This work contributes to the body of knowledge on sustainable finance by teaching investors how to use predictive strategies on the future values of their investments.

Quantitative Trading using Deep Q Learning

Abstract: Reinforcement learning (RL) is a branch of machine learning that has been used in a variety of applications such as robotics, game playing, and autonomous systems. In recent years, there has been growing interest in applying RL to quantitative trading, where the goal is to make profitable trades in financial markets. This paper explores the use of RL in quantitative trading and presents a case study of a RLbased trading algorithm. The results show that RL can be a powerful tool for quantitative trading, and that it has the potential to outperform traditional trading algorithms. The use of reinforcement learning in quantitative trading represents a promising area of research that can potentially lead to the development of more sophisticated and effective trading systems. Future work could explore the use of alternative reinforcement learning algorithms, incorporate additional data sources, and test the system on different asset classes. Overall, our research demonstrates the potential of using reinforcement learning in quantitative trading and highlights the importance of continued research and development in this area. By developing more sophisticated and effective trading systems, we can potentially improve the efficiency of financial markets and generate greater returns for investors

Is attention all you need for intraday Forex trading?

AbstractThe main objective of this paper is to analyse whether the Transformer neural network, which has become one of the most influential algorithms in Artificial Intelligence over the last few years, exhibits predictive capabilities for high‐frequency Forex data. The prediction task is to classify short‐term Forex movements for six currency pairs and five different time intervals from 60 to 720 min. We find that the Transformer exhibits high predictive power in the context of intraday Forex trading. This performance is slightly better than for the carefully selected benchmark – ResNet‐LSTM, which currently is a state‐of‐the‐art algorithm. Since intraday Forex trading based on deep learning models is largely unexplored, we offer insight on which currency pair and time interval are amenable to devising a profitable trading strategy. We also show that high predictive accuracy can be misleading in real world trading for short time intervals, as models trained on OHLC data tend to report the highest accuracy when the spread cost is the highest. This renders assessment based on typical machine learning metrics overly optimistic. Therefore, it is critical to backtest frequent intraday Forex trading strategies with realistic cost assumptions, which is rarely the case in empirical literature. Lastly, sensitivity analysis shows that the length of the time interval used for training does not play a critical role in the Transformer's predictive capabilities, whereas features derived from technical analysis are essential.

Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets

Cryptocurrency markets experienced a significant increase in the popularity, which motivated many financial traders to seek high profits in cryptocurrency trading. The predominant tool that traders use to identify profitable opportunities is technical analysis. Some investors and researchers also combined technical analysis with machine learning, in order to forecast upcoming trends in the market. However, even with the use of these methods, developing successful trading strategies is still regarded as an extremely challenging task. Recently, deep reinforcement learning (DRL) algorithms demonstrated satisfying performance in solving complicated problems, including the formulation of profitable trading strategies. While some DRL techniques have been successful in increasing profit and loss (PNL) measures, these techniques are not much risk-aware and present difficulty in maximizing PNL and lowering trading risks simultaneously. This research proposes the combination of DRL approaches with rule-based safety mechanisms to both maximize PNL returns and minimize trading risk. First, a DRL agent is trained to maximize PNL returns, using a novel reward function. Then, during the exploitation phase, a rule-based mechanism is deployed to prevent uncertain actions from being executed. Finally, another novel safety mechanism is proposed, which considers the actions of a more conservatively trained agent, in order to identify high-risk trading periods and avoid trading. Our experiments on 5 popular cryptocurrencies show that the integration of these three methods achieves very promising results.

Dynamic adjustment model of performance guarantee quota based on optimization decision of medium/long-term transactions of power selling companies

The existing mode of the fixed performance guarantee quota, which is susceptible to subjective determination, results in a lack of objectivity in the cost calculations of power selling companies, and has an impact on the calculation of their trading profits. Thus, it negatively impacts the stability of power market transactions as well as the operating enthusiasm of power selling company. Therefore, a dynamic adjustment strategy for performance guarantee quota is proposed, taking into account assessment criteria for the economic benefit of power selling companies, such as the degree of credit overdraft, the level of market share impact and national policies. Based on the fuzzy analytic hierarchy process (FAHP), the proposed dynamic adjustment model of the performance guarantee quota of power selling companies is established. To maximize the profit of power selling companies, the optimization decision of multiple types of transactions based on the proposed dynamic adjustment model of performance guarantee quota is carried out, such as decision-making of the medium/long-term transactions. Based on numerical simulations in MATLAB, the dynamic adjustment range of the performance guarantee quota is given. The suitability and effectiveness of the adjusted performance guarantee quota are verified by comparing and analyzing the differences, in the cost of power selling company in multiple scenarios.

Security requirement classification of electricity trading data based on hierarchical fuzzy Petri network

With the emergence of spot electricity trading, market-oriented trading has been intensively carried out, forming a multi-cycle trading system. In this process, a large amount of fine-grained electricity trading data circulates on the trading platform. Trading data is an important basis for decision-making in the electricity spot market, which directly affects the trading profits of market entities, proper disclosure of this information is very important for market enterprises. Information disclosure must ensure the validity and security. However, it is hard to judge the security demand for trading data, and there is no suitable evaluation system for determining the security requirement of data, which will limit the electricity market’s further development. In this paper, we first design an indicator system for security requirements classification, which manages data risks from three aspects: data classification, data risk, and entity demand. This system will guide us in determining data security requirements and further help identify differentiated data security protection schemes. Then, based on this system, we propose the classification method of data security requirements through a hierarchical fuzzy Petri net. The lower network realizes a reasonable assessment of data risk with reference to the index system, and the upper network finally determines the level of security requirements through the fuzzy rule base. Last, two types of data are selected to judge their security requirements. The results show that our method can provide a reference for privacy protection in electricity market data.

Discovering stories from Punjab on the streets of Saint-Tropez, Cote D’Azur, France

This paper presents stories associated with artefacts and episodes from the Kingdom of Lahore in Punjab, told through the author's research visit and fieldwork on the streets of Saint-Tropez located on the Cote D'Azur in the South of France. Episodes in the early 19th century that shaped the establishment of the Kingdom of Lahore, ruled by Maharajah Ranjit Singh, are outlined, and the author introduces Europeans employed in the armies of Punjab. The author describes how the actions of the Maharajah in the 1830s opened up highly profitable trading routes for some of his European generals between Lahore and Europe, dealing in arts, armour and textiles. The establishment of these Indo-French trading routes included the export of luxurious shawls from Kashmir and Amritsar (ruled at the time by Ranjit Singh) to Europe. One prominent individual, Jean-Francois Allard, who rose to become a general in Punjab, is chronicled, and the paper focuses on Allard and his wife, Bannou Pan Dei, and their life in Saint-Tropez. The paper ends by highlighting the recent work by officials in Saint-Tropez to articulate these stories and shared histories to develop interest, relations and promote tourism between the locations of India, especially Punjab and Himachal Pradesh, and France.

Homogeneous and Heterogeneous Effect of Agricultural Inputs on Crop Productivity of The Three-Grain Crop Types in Ethiopia

Agriculture is a critical source of food and income, making it a key component of poverty reduction and ensuring food security across the globe. The sector generates 88.8 percent of the trade profit and contributes 36.7 percent of GDP. The purpose of this paper is to identify the homogeneous and heterogeneous effects of agricultural inputs on crop productivity of three-grain crop types in Ethiopia using an appropriate PMG estimator, as well as to evaluate the effect of agricultural input heterogeneity and homogeneity across individual cross-sectional units (crops). The central statistical agency (CSA) provided the data for this study, which covered the entire country from 1990 to 2012 Ethiopian Calendar (E.C). In the long run, the study found that a one percent increase in fertilizer use resulted in a 2.686 percent increase in productivity of grain crops in Ethiopia, while a corresponding increase in improved seed per hectare and land size resulted in a 48.31 percent and 10.58 percent increase in productivity of grain crops per crop type, respectively. As the value of improved seed increased by one percent with a period lag among commercial farmers, the short-term production of cereal crops increased by 30.29 percent. Grain crop productivity improved by 40.6 percent when area increased by one percent at the first difference. The results of this study show that fertilizer use, improved seed use, and cropland size made homogeneous significant contributions to improved grain crop productivity in the long run across all cross-sectional units. However, in the short run, agricultural inputs such as pesticide use and improved seed use made heterogeneous significant contributions to the first lagged value

The impact and profitability of day trading following the relaxation of day trading restrictions in Taiwan

The relaxation of day trading restrictions in Taiwan at the start of 2016 resulted in a significant increase in day trading volume, which piqued our interest in researching the impact and profitability of day trading, expected (unexpected) day trading, and day trading at high (low) levels of VIX using time series models, with the following key findings. First, we show that a high market trading volume triggers a high day trading volume resulting from liquidity markets that day traders prefer, but a high day trading volume does not trigger a high market trading volume resulting from speculative markets that other market participants don't prefer. Second, contrary to our perception, while the VIX index rises, day trading would be more profitable after the relaxation. We infer that a high VIX index may be accompanied by a volatile market, which may generate profits by widening the intraday spread of a day-tradable stock. Third, as compared with unexpected market trading volume, we reveal that unexpected day trading volume may be more unexpected than market trading volume, being more likely to enhance market volatility and stock returns. These impressive and interesting findings may not be disclosed before the relaxation, which may contribute to the existing literature.

Application of Simulated Annealing Method on Tabarru-Fund Valuation using Inflator by Vasicek Model Approach Based on Profit and Loss Sharing Scheme

Currently, the financial services industry is dominated by conventional banks and individuals that apply the system of interest or an excess of loans. In Islam, this excess is referred to as usury, which is prohibited by Islamic law because, in practice, usury makes borrowers poorer as they cannot pay such high-interest installments. Not to mention, late payments are subject to penalties that will continue to accumulate if the borrower is unable to pay the next installment. From these facts, this system is prohibited by Islamic Law because there are harmed parties. Therefore, this research discusses mathematical models in the form of Islamic investment business loans for micro-economic traders by implementing a profit and loss sharing system. Tabarru-fund is a set of funds derived from borrowers’ contributions used to overcome conditions when they experience losses in certain conditions. In this mathematical model, the tabarru-fund acts as the premium that must be paid if the borrower is still profitable after the principal installments have paid off. This sharia model with tabarru funds is obtained by calculating the premium which involves the problem of minimizing the remaining tabarru funds in a certain period. The future value of the trader's profit rate will be projected using the Vasicek Model approach which previously determined the parameter estimation using OLS regression and then the data is generated using Monte Carlo simulation so that the sharia inflator is obtained. This sharia inflator plays a role in the optimization process of minimizing the remaining tabarru-fund which will be solved by the Simulated Annealing (SA) algorithm.

Sovereign Debt and Credit Default Swaps

How do credit default swaps (CDS) affect sovereign debt markets? The answer depends crucially on trading frictions, risk-sharing, arbitrage violations, and spillovers from secondary to primary markets. We propose a sovereign default model where investors trade bonds and CDS over the counter via directed search. CDS affect bond prices through several channels. First, CDS act as a synthetic bond. Second, CDS reduce bond-investing risks, allowing exposure to be unwound. Third, CDS availability increases trading profitability, which induces entry and reduces trading costs. Last, these direct effects feedback into default decisions. Our novel identification strategy exploits confidential microdata to quantify the extent of trading frictions and risk-sharing. The model generates realistic CDS-bond basis deviations, bid/ask spreads, and CDS volumes and positions. Our baseline specification predicts large effects of frictions generally but small spillovers from a naked CDS ban. These predictions hinge crucially on the identified parameters.