Current digital payment solutions are fragile and offer less privacy than traditional cash. Their critical dependency on an online service used to perform and validate transactions makes them void if this service is unreachable. Moreover, no transaction can be executed during server malfunctions or power outages. Due to climate change, the likelihood of extreme weather increases. As extreme weather is a major cause of power outages, the frequency of power outages is expected to increase. The lack of privacy is an inherent result of their account-based design or the use of a public ledger. The critical dependency and lack of privacy can be resolved with a Central Bank Digital Currency that can be used offline. This thesis proposes a design and a first implementation for an offline-first digital euro. The protocol offers complete privacy during transactions using zero-knowledge proofs. Furthermore, transactions can be executed offline without third parties and retroactive double-spending detection is facilitated. To protect the users' privacy, but also guard against money laundering, we have added the following privacy-guarding mechanism. The bank and trusted third parties for law enforcement must collaborate to decrypt transactions, revealing the digital pseudonym used in the transaction. Importantly, the transaction can be decrypted without decrypting prior transactions attached to the digital euro. The protocol has a working initial implementation showcasing its usability and demonstrating functionality.
{"title":"Offline Digital Euro: a Minimum Viable CBDC using Groth-Sahai proofs","authors":"Leon Kempen, Johan Pouwelse","doi":"arxiv-2407.13776","DOIUrl":"https://doi.org/arxiv-2407.13776","url":null,"abstract":"Current digital payment solutions are fragile and offer less privacy than\u0000traditional cash. Their critical dependency on an online service used to perform and validate\u0000transactions makes them void if this service is unreachable. Moreover, no transaction can be executed during server malfunctions or power\u0000outages. Due to climate change, the likelihood of extreme weather increases. As\u0000extreme weather is a major cause of power outages, the frequency of power\u0000outages is expected to increase. The lack of privacy is an inherent result of their account-based design or\u0000the use of a public ledger. The critical dependency and lack of privacy can be resolved with a Central\u0000Bank Digital Currency that can be used offline. This thesis proposes a design and a first implementation for an offline-first\u0000digital euro. The protocol offers complete privacy during transactions using zero-knowledge\u0000proofs. Furthermore, transactions can be executed offline without third parties and\u0000retroactive double-spending detection is facilitated. To protect the users' privacy, but also guard against money laundering, we\u0000have added the following privacy-guarding mechanism. The bank and trusted third parties for law enforcement must collaborate to\u0000decrypt transactions, revealing the digital pseudonym used in the transaction. Importantly, the transaction can be decrypted without decrypting prior\u0000transactions attached to the digital euro. The protocol has a working initial implementation showcasing its usability\u0000and demonstrating functionality.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alireza Mohammadshafie, Akram Mirzaeinia, Haseebullah Jumakhan, Amir Mirzaeinia
Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and SAC engage in significant trades with a limited number of stocks, DDPG and TD3 adopt a more balanced approach. Furthermore, SAC and PPO tend to hold positions for shorter durations, whereas DDPG, A2C, and TD3 display a propensity to remain stationary for extended periods.
{"title":"Deep Reinforcement Learning Strategies in Finance: Insights into Asset Holding, Trading Behavior, and Purchase Diversity","authors":"Alireza Mohammadshafie, Akram Mirzaeinia, Haseebullah Jumakhan, Amir Mirzaeinia","doi":"arxiv-2407.09557","DOIUrl":"https://doi.org/arxiv-2407.09557","url":null,"abstract":"Recent deep reinforcement learning (DRL) methods in finance show promising\u0000outcomes. However, there is limited research examining the behavior of these\u0000DRL algorithms. This paper aims to investigate their tendencies towards holding\u0000or trading financial assets as well as purchase diversity. By analyzing their\u0000trading behaviors, we provide insights into the decision-making processes of\u0000DRL models in finance applications. Our findings reveal that each DRL algorithm\u0000exhibits unique trading patterns and strategies, with A2C emerging as the top\u0000performer in terms of cumulative rewards. While PPO and SAC engage in\u0000significant trades with a limited number of stocks, DDPG and TD3 adopt a more\u0000balanced approach. Furthermore, SAC and PPO tend to hold positions for shorter\u0000durations, whereas DDPG, A2C, and TD3 display a propensity to remain stationary\u0000for extended periods.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141721378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuan Li, Bingqiao Luo, Qian Wang, Nuo Chen, Xu Liu, Bingsheng He
The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at url{https://anonymous.4open.science/r/CryptoTrade-Public-92FC/}.
{"title":"A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading","authors":"Yuan Li, Bingqiao Luo, Qian Wang, Nuo Chen, Xu Liu, Bingsheng He","doi":"arxiv-2407.09546","DOIUrl":"https://doi.org/arxiv-2407.09546","url":null,"abstract":"The utilization of Large Language Models (LLMs) in financial trading has\u0000primarily been concentrated within the stock market, aiding in economic and\u0000financial decisions. Yet, the unique opportunities presented by the\u0000cryptocurrency market, noted for its on-chain data's transparency and the\u0000critical influence of off-chain signals like news, remain largely untapped by\u0000LLMs. This work aims to bridge the gap by developing an LLM-based trading\u0000agent, CryptoTrade, which uniquely combines the analysis of on-chain and\u0000off-chain data. This approach leverages the transparency and immutability of\u0000on-chain data, as well as the timeliness and influence of off-chain signals,\u0000providing a comprehensive overview of the cryptocurrency market. CryptoTrade\u0000incorporates a reflective mechanism specifically engineered to refine its daily\u0000trading decisions by analyzing the outcomes of prior trading decisions. This\u0000research makes two significant contributions. Firstly, it broadens the\u0000applicability of LLMs to the domain of cryptocurrency trading. Secondly, it\u0000establishes a benchmark for cryptocurrency trading strategies. Through\u0000extensive experiments, CryptoTrade has demonstrated superior performance in\u0000maximizing returns compared to traditional trading strategies and time-series\u0000baselines across various cryptocurrencies and market conditions. Our code and\u0000data are available at\u0000url{https://anonymous.4open.science/r/CryptoTrade-Public-92FC/}.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"74 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141721327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA. This unique algorithm uses LSTM to produce final predictions but boosts the results of this RNN by adding the residuals obtained from ARIMA predictions among other inputs. The algorithm is tested across three equity indices (S&P 500, FTSE 100, and CAC 40) using daily frequency data from January 2000 to August 2023. The testing architecture is based on the walk-forward procedure for the hyperparameter tunning phase that uses Random Search and backtesting the algorithms. The selection of the optimal model is determined based on adequately selected performance metrics focused on risk-adjusted return measures. We considered two strategies for each algorithm: Long-Only and Long-Short to present the situation of two various groups of investors with different investment policy restrictions. For each strategy and equity index, we compute the performance metrics and visualize the equity curve to identify the best strategy with the highest modified information ratio. The findings conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms across all the equity indices which confirms the strong potential behind hybrid ML-TS (machine learning - time series) models in searching for the optimal algorithmic investment strategies.
{"title":"LSTM-ARIMA as a Hybrid Approach in Algorithmic Investment Strategies","authors":"Kamil Kashif, Robert Ślepaczuk","doi":"arxiv-2406.18206","DOIUrl":"https://doi.org/arxiv-2406.18206","url":null,"abstract":"This study focuses on building an algorithmic investment strategy employing a\u0000hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA.\u0000This unique algorithm uses LSTM to produce final predictions but boosts the\u0000results of this RNN by adding the residuals obtained from ARIMA predictions\u0000among other inputs. The algorithm is tested across three equity indices (S&P\u0000500, FTSE 100, and CAC 40) using daily frequency data from January 2000 to\u0000August 2023. The testing architecture is based on the walk-forward procedure\u0000for the hyperparameter tunning phase that uses Random Search and backtesting\u0000the algorithms. The selection of the optimal model is determined based on\u0000adequately selected performance metrics focused on risk-adjusted return\u0000measures. We considered two strategies for each algorithm: Long-Only and\u0000Long-Short to present the situation of two various groups of investors with\u0000different investment policy restrictions. For each strategy and equity index,\u0000we compute the performance metrics and visualize the equity curve to identify\u0000the best strategy with the highest modified information ratio. The findings\u0000conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms\u0000across all the equity indices which confirms the strong potential behind hybrid\u0000ML-TS (machine learning - time series) models in searching for the optimal\u0000algorithmic investment strategies.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"347 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, Bo An
High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, emph{e.g.,} hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, emph{a.k.a.} MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making. Extensive experiments on various cryptocurrency markets demonstrate that MacroHFT can achieve state-of-the-art performance on minute-level trading tasks.
{"title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","authors":"Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, Bo An","doi":"arxiv-2406.14537","DOIUrl":"https://doi.org/arxiv-2406.14537","url":null,"abstract":"High-frequency trading (HFT) that executes algorithmic trading in short time\u0000scales, has recently occupied the majority of cryptocurrency market. Besides\u0000traditional quantitative trading methods, reinforcement learning (RL) has\u0000become another appealing approach for HFT due to its terrific ability of\u0000handling high-dimensional financial data and solving sophisticated sequential\u0000decision-making problems, emph{e.g.,} hierarchical reinforcement learning\u0000(HRL) has shown its promising performance on second-level HFT by training a\u0000router to select only one sub-agent from the agent pool to execute the current\u0000transaction. However, existing RL methods for HFT still have some defects: 1)\u0000standard RL-based trading agents suffer from the overfitting issue, preventing\u0000them from making effective policy adjustments based on financial context; 2)\u0000due to the rapid changes in market conditions, investment decisions made by an\u0000individual agent are usually one-sided and highly biased, which might lead to\u0000significant loss in extreme markets. To tackle these problems, we propose a\u0000novel Memory Augmented Context-aware Reinforcement learning method On HFT,\u0000emph{a.k.a.} MacroHFT, which consists of two training phases: 1) we first\u0000train multiple types of sub-agents with the market data decomposed according to\u0000various financial indicators, specifically market trend and volatility, where\u0000each agent owns a conditional adapter to adjust its trading policy according to\u0000market conditions; 2) then we train a hyper-agent to mix the decisions from\u0000these sub-agents and output a consistently profitable meta-policy to handle\u0000rapid market fluctuations, equipped with a memory mechanism to enhance the\u0000capability of decision-making. Extensive experiments on various cryptocurrency\u0000markets demonstrate that MacroHFT can achieve state-of-the-art performance on\u0000minute-level trading tasks.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"97 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peter Klimek, Maximilian Hess, Markus Gerschberger, Stefan Thurner
The steel industry is a major contributor to CO2 emissions, accounting for 7% of global emissions. The European steel industry is seeking to reduce its emissions by increasing the use of electric arc furnaces (EAFs), which can produce steel from scrap, marking a major shift towards a circular steel economy. Here, we show by combining trade with business intelligence data that this shift requires a deep restructuring of the global and European scrap trade, as well as a substantial scaling of the underlying business ecosystem. We find that the scrap imports of European countries with major EAF installations have steadily decreased since 2007 while globally scrap trade started to increase recently. Our statistical modelling shows that every 1,000 tonnes of EAF capacity installed is associated with an increase in annual imports of 550 tonnes and a decrease in annual exports of 1,000 tonnes of scrap, suggesting increased competition for scrap metal as countries ramp up their EAF capacity. Furthermore, each scrap company enables an increase of around 79,000 tonnes of EAF-based steel production per year in the EU. Taking these relations as causal and extrapolating to the currently planned EAF capacity, we find that an additional 730 (SD 140) companies might be required, employing about 35,000 people (IQR 29,000-50,000) and generating an additional estimated turnover of USD 35 billion (IQR 27-48). Our results thus suggest that scrap metal is likely to become a strategic resource. They highlight the need for a massive restructuring of the industry's supply networks and identify the resulting growth opportunities for companies.
{"title":"Circular transformation of the European steel industry renders scrap metal a strategic resource","authors":"Peter Klimek, Maximilian Hess, Markus Gerschberger, Stefan Thurner","doi":"arxiv-2406.12098","DOIUrl":"https://doi.org/arxiv-2406.12098","url":null,"abstract":"The steel industry is a major contributor to CO2 emissions, accounting for 7%\u0000of global emissions. The European steel industry is seeking to reduce its\u0000emissions by increasing the use of electric arc furnaces (EAFs), which can\u0000produce steel from scrap, marking a major shift towards a circular steel\u0000economy. Here, we show by combining trade with business intelligence data that\u0000this shift requires a deep restructuring of the global and European scrap\u0000trade, as well as a substantial scaling of the underlying business ecosystem.\u0000We find that the scrap imports of European countries with major EAF\u0000installations have steadily decreased since 2007 while globally scrap trade\u0000started to increase recently. Our statistical modelling shows that every 1,000\u0000tonnes of EAF capacity installed is associated with an increase in annual\u0000imports of 550 tonnes and a decrease in annual exports of 1,000 tonnes of\u0000scrap, suggesting increased competition for scrap metal as countries ramp up\u0000their EAF capacity. Furthermore, each scrap company enables an increase of\u0000around 79,000 tonnes of EAF-based steel production per year in the EU. Taking\u0000these relations as causal and extrapolating to the currently planned EAF\u0000capacity, we find that an additional 730 (SD 140) companies might be required,\u0000employing about 35,000 people (IQR 29,000-50,000) and generating an additional\u0000estimated turnover of USD 35 billion (IQR 27-48). Our results thus suggest that\u0000scrap metal is likely to become a strategic resource. They highlight the need\u0000for a massive restructuring of the industry's supply networks and identify the\u0000resulting growth opportunities for companies.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a deep learning approach to study the minimal variance pricing and hedging problem in an incomplete jump diffusion market. It is based upon a rigorous stochastic calculus derivation of the optimal hedging portfolio, optimal option price, and the corresponding equivalent martingale measure through the means of the Stackelberg game approach. A deep learning algorithm based on the combination of the feedforward and LSTM neural networks is tested on three different market models, two of which are incomplete. In contrast, the complete market Black-Scholes model serves as a benchmark for the algorithm's performance. The results that indicate the algorithm's good performance are presented and discussed. In particular, we apply our results to the special incomplete market model studied by Merton and give a detailed comparison between our results based on the minimal variance principle and the results obtained by Merton based on a different pricing principle. Using deep learning, we find that the minimal variance principle leads to typically higher option prices than those deduced from the Merton principle. On the other hand, the minimal variance principle leads to lower losses than the Merton principle.
{"title":"Deep learning for quadratic hedging in incomplete jump market","authors":"Nacira Agram, Bernt Øksendal, Jan Rems","doi":"arxiv-2407.13688","DOIUrl":"https://doi.org/arxiv-2407.13688","url":null,"abstract":"We propose a deep learning approach to study the minimal variance pricing and\u0000hedging problem in an incomplete jump diffusion market. It is based upon a\u0000rigorous stochastic calculus derivation of the optimal hedging portfolio,\u0000optimal option price, and the corresponding equivalent martingale measure\u0000through the means of the Stackelberg game approach. A deep learning algorithm\u0000based on the combination of the feedforward and LSTM neural networks is tested\u0000on three different market models, two of which are incomplete. In contrast, the\u0000complete market Black-Scholes model serves as a benchmark for the algorithm's\u0000performance. The results that indicate the algorithm's good performance are\u0000presented and discussed. In particular, we apply our results to the special incomplete market model\u0000studied by Merton and give a detailed comparison between our results based on\u0000the minimal variance principle and the results obtained by Merton based on a\u0000different pricing principle. Using deep learning, we find that the minimal\u0000variance principle leads to typically higher option prices than those deduced\u0000from the Merton principle. On the other hand, the minimal variance principle\u0000leads to lower losses than the Merton principle.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"93 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sven Goluža, Tomislav Kovačević, Tessa Bauman, Zvonko Kostanjčar
Deep reinforcement learning (DRL) is a well-suited approach to financial decision-making, where an agent makes decisions based on its trading strategy developed from market observations. Existing DRL intraday trading strategies mainly use price-based features to construct the state space. They neglect the contextual information related to the position of the strategy, which is an important aspect given the sequential nature of intraday trading. In this study, we propose a novel DRL model for intraday trading that introduces positional features encapsulating the contextual information into its sparse state space. The model is evaluated over an extended period of almost a decade and across various assets including commodities and foreign exchange securities, taking transaction costs into account. The results show a notable performance in terms of profitability and risk-adjusted metrics. The feature importance results show that each feature incorporating contextual information contributes to the overall performance of the model. Additionally, through an exploration of the agent's intraday trading activity, we unveil patterns that substantiate the effectiveness of our proposed model.
{"title":"Deep reinforcement learning with positional context for intraday trading","authors":"Sven Goluža, Tomislav Kovačević, Tessa Bauman, Zvonko Kostanjčar","doi":"arxiv-2406.08013","DOIUrl":"https://doi.org/arxiv-2406.08013","url":null,"abstract":"Deep reinforcement learning (DRL) is a well-suited approach to financial\u0000decision-making, where an agent makes decisions based on its trading strategy\u0000developed from market observations. Existing DRL intraday trading strategies\u0000mainly use price-based features to construct the state space. They neglect the\u0000contextual information related to the position of the strategy, which is an\u0000important aspect given the sequential nature of intraday trading. In this\u0000study, we propose a novel DRL model for intraday trading that introduces\u0000positional features encapsulating the contextual information into its sparse\u0000state space. The model is evaluated over an extended period of almost a decade\u0000and across various assets including commodities and foreign exchange\u0000securities, taking transaction costs into account. The results show a notable\u0000performance in terms of profitability and risk-adjusted metrics. The feature\u0000importance results show that each feature incorporating contextual information\u0000contributes to the overall performance of the model. Additionally, through an\u0000exploration of the agent's intraday trading activity, we unveil patterns that\u0000substantiate the effectiveness of our proposed model.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a theory of stock market predictability patterns based on a model of heterogeneous beliefs. In a discrete finite time framework, some agents receive news about an asset's fundamental value through a noisy signal. The investors are heterogeneous in that they have different beliefs about the stochastic supply. A momentum in the stock price arises from those agents who incorrectly underestimate the signal accuracy, dampening the initial price impact of the signal. A reversal in price occurs because the price reverts to the fundamental value in the long run. An extension of the model to multiple assets case predicts co-movement and lead-lag effect, in addition to cross-sectional momentum and reversal. The heterogeneous beliefs of investors about news demonstrate how the main predictability anomalies arise endogenously in a model of bounded rationality.
{"title":"Heterogeneous Beliefs Model of Stock Market Predictability","authors":"Jiho Park","doi":"arxiv-2406.08448","DOIUrl":"https://doi.org/arxiv-2406.08448","url":null,"abstract":"This paper proposes a theory of stock market predictability patterns based on\u0000a model of heterogeneous beliefs. In a discrete finite time framework, some\u0000agents receive news about an asset's fundamental value through a noisy signal.\u0000The investors are heterogeneous in that they have different beliefs about the\u0000stochastic supply. A momentum in the stock price arises from those agents who\u0000incorrectly underestimate the signal accuracy, dampening the initial price\u0000impact of the signal. A reversal in price occurs because the price reverts to\u0000the fundamental value in the long run. An extension of the model to multiple\u0000assets case predicts co-movement and lead-lag effect, in addition to\u0000cross-sectional momentum and reversal. The heterogeneous beliefs of investors\u0000about news demonstrate how the main predictability anomalies arise endogenously\u0000in a model of bounded rationality.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141508457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Trend following and momentum investing are common strategies employed by asset managers. Even though they can be helpful in the proper situations, they are limited in the sense that they work just by looking at past, as if we were driving with our focus on the rearview mirror. In this paper, we advocate for the use of Artificial Intelligence and Machine Learning techniques to predict future market trends. These predictions, when done properly, can improve the performance of asset managers by increasing returns and reducing drawdowns.
{"title":"Beyond Trend Following: Deep Learning for Market Trend Prediction","authors":"Fernando Berzal, Alberto Garcia","doi":"arxiv-2407.13685","DOIUrl":"https://doi.org/arxiv-2407.13685","url":null,"abstract":"Trend following and momentum investing are common strategies employed by\u0000asset managers. Even though they can be helpful in the proper situations, they\u0000are limited in the sense that they work just by looking at past, as if we were\u0000driving with our focus on the rearview mirror. In this paper, we advocate for\u0000the use of Artificial Intelligence and Machine Learning techniques to predict\u0000future market trends. These predictions, when done properly, can improve the\u0000performance of asset managers by increasing returns and reducing drawdowns.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：