This paper offers a novel perspective on the implications of increasingly autonomous and “black box” algorithms, within the ramification of algorithmic trading, for the integrity of capital markets. Artificial intelligence (AI) and particularly its subfield of machine learning (ML) methods have gained immense popularity among the great public and achieved tremendous success in many real-life applications by leading to vast efficiency gains. In the financial trading domain, ML can augment human capabilities in both price prediction, dynamic portfolio optimization, and other financial decision-making tasks. However, thanks to constant progress in the ML technology, the prospect of increasingly capable and autonomous agents to delegate operational tasks and even decision-making is now beyond mere imagination, thus opening up the possibility for approximating (truly) autonomous trading agents anytime soon. Given these spectacular developments, this paper argues that such autonomous algorithmic traders may involve significant risks to market integrity, independent from their human experts, thanks to self-learning capabilities offered by state-of-the-art and innovative ML methods. Using the proprietary trading industry as a case study, we explore emerging threats to the application of established market abuse laws in the event of algorithmic market abuse, by taking an interdisciplinary stance between financial regulation, law & economics, and computational finance. Specifically, our analysis focuses on two emerging market abuse risks by autonomous algorithms: market manipulation and “tacit” collusion. We explore their likelihood to arise on global capital markets and evaluate related social harm as forms of market failures. With these new risks in mind, this paper questions the adequacy of existing regulatory frameworks and enforcement mechanisms, as well as current legal rules on the governance of algorithmic trading, to cope with increasingly autonomous and ubiquitous algorithmic trading systems. It shows how the “black box” nature of specific ML-powered algorithmic trading strategies can subvert existing market abuse laws, which are based upon traditional liability concepts and tests (such as “intent” and “causation”). In concluding, by addressing the shortcomings of the present legal framework, we develop a number of guiding principles to assist legal and policy reform in the spirit of promoting and safeguarding market integrity and safety.
{"title":"Machine Learning, Market Manipulation and Collusion on Capital Markets: Why the 'Black Box' matters","authors":"Alessio Azzutti, W. Ringe, H. Siegfried Stiehl","doi":"10.2139/ssrn.3788872","DOIUrl":"https://doi.org/10.2139/ssrn.3788872","url":null,"abstract":"This paper offers a novel perspective on the implications of increasingly autonomous and “black box” algorithms, within the ramification of algorithmic trading, for the integrity of capital markets. Artificial intelligence (AI) and particularly its subfield of machine learning (ML) methods have gained immense popularity among the great public and achieved tremendous success in many real-life applications by leading to vast efficiency gains. In the financial trading domain, ML can augment human capabilities in both price prediction, dynamic portfolio optimization, and other financial decision-making tasks. However, thanks to constant progress in the ML technology, the prospect of increasingly capable and autonomous agents to delegate operational tasks and even decision-making is now beyond mere imagination, thus opening up the possibility for approximating (truly) autonomous trading agents anytime soon. \u0000 \u0000Given these spectacular developments, this paper argues that such autonomous algorithmic traders may involve significant risks to market integrity, independent from their human experts, thanks to self-learning capabilities offered by state-of-the-art and innovative ML methods. Using the proprietary trading industry as a case study, we explore emerging threats to the application of established market abuse laws in the event of algorithmic market abuse, by taking an interdisciplinary stance between financial regulation, law & economics, and computational finance. Specifically, our analysis focuses on two emerging market abuse risks by autonomous algorithms: market manipulation and “tacit” collusion. We explore their likelihood to arise on global capital markets and evaluate related social harm as forms of market failures. \u0000 \u0000With these new risks in mind, this paper questions the adequacy of existing regulatory frameworks and enforcement mechanisms, as well as current legal rules on the governance of algorithmic trading, to cope with increasingly autonomous and ubiquitous algorithmic trading systems. It shows how the “black box” nature of specific ML-powered algorithmic trading strategies can subvert existing market abuse laws, which are based upon traditional liability concepts and tests (such as “intent” and “causation”). In concluding, by addressing the shortcomings of the present legal framework, we develop a number of guiding principles to assist legal and policy reform in the spirit of promoting and safeguarding market integrity and safety.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116103962","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 apply the two-step machine-learning method proposed by Claveria et al. (2021) to generate country-specific sentiment indicators that provide estimates of year-on-year GDP growth rates. In the first step, by means of genetic programming, business and consumer expectations are evolved to derive sentiment indicators for 19 European economies. In the second step, the sentiment indicators are iteratively re-computed and combined each period to forecast yearly growth rates. To assess the performance of the proposed approach, we have designed two out-of-sample experiments: a nowcasting exercise in which we recursively generate estimates of GDP at the end of each quarter using the latest survey data available, and an iterative forecasting exercise for different forecast horizons We found that forecasts generated with the sentiment indicators outperform those obtained with time series models. These results show the potential of the methodology as a predictive tool.
{"title":"Nowcasting and Forecasting GDP Growth with Machine-Learning Sentiment Indicators","authors":"Oscar Claveria, E. Monte, Salvador Torra","doi":"10.2139/ssrn.3787570","DOIUrl":"https://doi.org/10.2139/ssrn.3787570","url":null,"abstract":"We apply the two-step machine-learning method proposed by Claveria et al. (2021) to generate country-specific sentiment indicators that provide estimates of year-on-year GDP growth rates. In the first step, by means of genetic programming, business and consumer expectations are evolved to derive sentiment indicators for 19 European economies. In the second step, the sentiment indicators are iteratively re-computed and combined each period to forecast yearly growth rates. To assess the performance of the proposed approach, we have designed two out-of-sample experiments: a nowcasting exercise in which we recursively generate estimates of GDP at the end of each quarter using the latest survey data available, and an iterative forecasting exercise for different forecast horizons We found that forecasts generated with the sentiment indicators outperform those obtained with time series models. These results show the potential of the methodology as a predictive tool.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132081113","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}
Miquel Noguer i Alonso, G. Batres-Estrada, Aymeric Moulin
We examine the performance of Deep Learning methods applied to equity financial time series. Predicting equity time series is a crucial topic in Finance. To form equity portfolios and do asset allocation, we need to predict returns, compute their risk, and optimize market impact. One of the modeling benefits of Deep Learning architectures is the ability to model non-linear highly dimensional problems. The lack of transparency and a rigorous mathematical theory could be considered less positive sides. The fact that most progress in Deep Learning has been made by trial and error is also cumbersome. Equity financial time series is a challenging domain with some stylized facts: weak stationarity, fat tails in return distributions, small data sets compared to other areas of Artificial Intelligence (AI), slow decay of autocorrelation in returns, and volatility clustering, to name the most important ones. We perform a comparative study between Long ShortTerm Memory Networks (LSTM), Recurrent Neural Networks (RNN), Deep Feed-Forward neural networks (DNN), and Gated Recurrent Unit Networks (GRU). We perform two types of studies. The first focused on a univariate test, and the second a multivariate test. Our tests show that the LSTM performs the best compared to other Deep Learning and classical machine learning models. In terms of performance metrics, the LSTM is better than the baseline model. We also show that the predictions are better than chance. There is enough evidence thatRNN and LSTM can deal with stationary time series and learn the data generating process. Nevertheless, predicting equity non-stationary time series, with market developments like the one caused by the COVID-19 pandemic in 2020, is challenging.
{"title":"Deep Learning for Equity Time Series Prediction","authors":"Miquel Noguer i Alonso, G. Batres-Estrada, Aymeric Moulin","doi":"10.2139/ssrn.3735940","DOIUrl":"https://doi.org/10.2139/ssrn.3735940","url":null,"abstract":"We examine the performance of Deep Learning methods applied to equity financial time series. Predicting equity time series is a crucial topic in Finance. To form equity portfolios and do asset allocation, we need to predict returns, compute their risk, and optimize market impact. One of the modeling benefits of Deep Learning architectures is the ability to model non-linear highly dimensional problems. The lack of transparency and a rigorous mathematical theory could be considered less positive sides. The fact that most progress in Deep Learning has been made by trial and error is also cumbersome. Equity financial time series is a challenging domain with some stylized facts: weak stationarity, fat tails in return distributions, small data sets compared to other areas of Artificial Intelligence (AI), slow decay of autocorrelation in returns, and volatility clustering, to name the most important ones. We perform a comparative study between Long ShortTerm Memory Networks (LSTM), Recurrent Neural Networks (RNN), Deep Feed-Forward neural networks (DNN), and Gated Recurrent Unit Networks (GRU). We perform two types of studies. The first focused on a univariate test, and the second a multivariate test. Our tests show that the LSTM performs the best compared to other Deep Learning and classical machine learning models. In terms of performance metrics, the LSTM is better than the baseline model. We also show that the predictions are better than chance. There is enough evidence thatRNN and LSTM can deal with stationary time series and learn the data generating process. Nevertheless, predicting equity non-stationary time series, with market developments like the one caused by the COVID-19 pandemic in 2020, is challenging.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129745815","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}
Software defect prediction is a process of constructing machine learning classifiers to predict defective code snippets, using historical information in software repositories such as code complexity and change records to design software defect metrics , In this research article we have tried to understand the relationships between various variables which are important for IT SME’s ,The study is carried out with the help of a well structured questionnaire using IBM SPSS tool for data analysis and interpretation.
{"title":"An Exploratory Study in SME’s for Software Defect Prediction","authors":"S. Gollagi, P. Pareek","doi":"10.2139/ssrn.3734911","DOIUrl":"https://doi.org/10.2139/ssrn.3734911","url":null,"abstract":"Software defect prediction is a process of constructing machine learning classifiers to predict defective code snippets, using historical information in software repositories such as code complexity and change records to design software defect metrics , In this research article we have tried to understand the relationships between various variables which are important for IT SME’s ,The study is carried out with the help of a well structured questionnaire using IBM SPSS tool for data analysis and interpretation.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123360575","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}
Qing Yang, Zhenning Hong, Ruyan Tian, Tingting Ye, Liangliang Zhang
In this paper, we document a novel machine learning based bottom-up approach for static and dynamic portfolio optimization on, potentially, a large number of assets. The methodology overcomes many major difficulties arising in current optimization schemes. For example, we no longer need to compute the covariance matrix and its inverse for mean-variance optimization, therefore the method is immune from the estimation error on this quantity. Moreover, no explicit calls of optimization routines are needed. Applications to a bottom-up mean-variance-skewness-kurtosis or CRRA (Constant Relative Risk Aversion) optimization with short-sale portfolio constraints in both simulation and real market (China A-shares and U.S. equity markets) environments are studied and shown to perform very well.
{"title":"Asset Allocation via Machine Learning and Applications to Equity Portfolio Management","authors":"Qing Yang, Zhenning Hong, Ruyan Tian, Tingting Ye, Liangliang Zhang","doi":"10.2139/ssrn.3722621","DOIUrl":"https://doi.org/10.2139/ssrn.3722621","url":null,"abstract":"In this paper, we document a novel machine learning based bottom-up approach for static and dynamic portfolio optimization on, potentially, a large number of assets. The methodology overcomes many major difficulties arising in current optimization schemes. For example, we no longer need to compute the covariance matrix and its inverse for mean-variance optimization, therefore the method is immune from the estimation error on this quantity. Moreover, no explicit calls of optimization routines are needed. Applications to a bottom-up mean-variance-skewness-kurtosis or CRRA (Constant Relative Risk Aversion) optimization with short-sale portfolio constraints in both simulation and real market (China A-shares and U.S. equity markets) environments are studied and shown to perform very well.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124885871","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}
Technological development has led to rich datasets, fast processing capabilities, and a large body of literature on accurate yet complex models. However, although managers see potential in becoming data-driven, few successfully apply contemporary analytics. In retailing, some of the hurdles are that (a) most applications are for online settings, while most retailing is still conducted in brick-and-mortar settings, (b) predictions of customer lifetime values are less relevant for rapid (automated) actions in real-time, and (c) there is skepticism due to the lack of empirical testing beyond large international firms, tech start-ups, and digital natives. In this study, we attempt to bridge this gap by exploring the potential benefits of automated machine learning compared to manager heuristics in predicting immediate future customer value in real-time, as applied on 338,184 grocery receipts, 179,568 beauty receipts, and 111,289 non-prescription pharmacy receipts. Our results from different retailing industries with various product characteristics in brick-and-mortar contexts show that automated machine learning provides great benefits in predicting immediate future customer value. This suggests that, even with limited know-how, brick-and-mortar retailers can implement contemporary analytics for better customer prioritization in real-time.
{"title":"Man(ager Heuristics) vs. Machine (Learning): Automation for Prediction of Customer Value for Brick-and-Mortar Retailers","authors":"Emelie Fröberg, S. Rosengren","doi":"10.2139/ssrn.3772725","DOIUrl":"https://doi.org/10.2139/ssrn.3772725","url":null,"abstract":"Technological development has led to rich datasets, fast processing capabilities, and a large body of literature on accurate yet complex models. However, although managers see potential in becoming data-driven, few successfully apply contemporary analytics. In retailing, some of the hurdles are that (a) most applications are for online settings, while most retailing is still conducted in brick-and-mortar settings, (b) predictions of customer lifetime values are less relevant for rapid (automated) actions in real-time, and (c) there is skepticism due to the lack of empirical testing beyond large international firms, tech start-ups, and digital natives. In this study, we attempt to bridge this gap by exploring the potential benefits of automated machine learning compared to manager heuristics in predicting immediate future customer value in real-time, as applied on 338,184 grocery receipts, 179,568 beauty receipts, and 111,289 non-prescription pharmacy receipts. Our results from different retailing industries with various product characteristics in brick-and-mortar contexts show that automated machine learning provides great benefits in predicting immediate future customer value. This suggests that, even with limited know-how, brick-and-mortar retailers can implement contemporary analytics for better customer prioritization in real-time.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246624","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}
Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. It is first a prediction problem for expected returns and covariance matrix and then an optimization problem for returns, risk, and market impact. Investors and financial researchers have been working with approaches like mean-variance optimization, minimum variance, risk parity, and equally weighted and several methods to make expected returns and covariance matrices' predictions more robust. This paper demonstrates the application of reinforcement learning to create a financial model-free solution to the asset allocation problem, learning to solve the problem using time series and deep neural networks. We demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. We use a deep reinforcement model on US stocks using different architectures. We use Long Short Term Memory networks, Convolutional Neural Networks, and Recurrent Neural Networks and compare them with more traditional portfolio management. The Deep Reinforcement Learning approach shows better results than traditional approaches using a simple reward function and only being given the time series of stocks. In Finance, no training to test error generalization results come guaranteed. We can say that the modeling framework can deal with time series prediction and asset allocation, including transaction costs.
{"title":"Deep Reinforcement Learning for Asset Allocation in US Equities","authors":"Miquel Noguer i Alonso, Sonam Srivastava","doi":"10.2139/ssrn.3711487","DOIUrl":"https://doi.org/10.2139/ssrn.3711487","url":null,"abstract":"Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems. Asset allocation, where the goal is to obtain the weights of the assets that maximize the rewards in a given state of the market considering risk and transaction costs, is a problem easily framed using a reinforcement learning framework. It is first a prediction problem for expected returns and covariance matrix and then an optimization problem for returns, risk, and market impact. Investors and financial researchers have been working with approaches like mean-variance optimization, minimum variance, risk parity, and equally weighted and several methods to make expected returns and covariance matrices' predictions more robust. This paper demonstrates the application of reinforcement learning to create a financial model-free solution to the asset allocation problem, learning to solve the problem using time series and deep neural networks. We demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. We use a deep reinforcement model on US stocks using different architectures. We use Long Short Term Memory networks, Convolutional Neural Networks, and Recurrent Neural Networks and compare them with more traditional portfolio management. The Deep Reinforcement Learning approach shows better results than traditional approaches using a simple reward function and only being given the time series of stocks. In Finance, no training to test error generalization results come guaranteed. We can say that the modeling framework can deal with time series prediction and asset allocation, including transaction costs.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131747011","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}
E. Benhamou, D. Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay, J. Atif
Can an agent learn efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations? Through trading bots, we illustrate how Deep Reinforcement Learning (DRL) can tackle this challenge. Our contributions are threefold: (i) the use of contextual information also referred to as augmented state in DRL, (ii) the impact of a one period lag between observations and actions that is more realistic for an asset management environment , (iii) the implementation of a new repetitive train test method called walk forward analysis, similar in spirit to cross validation for time series. Although our experiment is on trading bots, it can easily be translated to other bot environments that operate in sequential environment with regime changes and noisy data. Our experiment for an augmented asset manager interested in finding the best portfolio for hedging strategies shows that AAMDRL achieves superior returns and lower risk.
{"title":"AAMDRL: Augmented Asset Management With Deep Reinforcement Learning","authors":"E. Benhamou, D. Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay, J. Atif","doi":"10.2139/ssrn.3702113","DOIUrl":"https://doi.org/10.2139/ssrn.3702113","url":null,"abstract":"Can an agent learn efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations? Through trading bots, we illustrate how Deep Reinforcement Learning (DRL) can tackle this challenge. Our contributions are threefold: (i) the use of contextual information also referred to as augmented state in DRL, (ii) the impact of a one period lag between observations and actions that is more realistic for an asset management environment , (iii) the implementation of a new repetitive train test method called walk forward analysis, similar in spirit to cross validation for time series. Although our experiment is on trading bots, it can easily be translated to other bot environments that operate in sequential environment with regime changes and noisy data. Our experiment for an augmented asset manager interested in finding the best portfolio for hedging strategies shows that AAMDRL achieves superior returns and lower risk.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421527","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 reinforcement learning (RL) framework to solve the HJB equations of optimal market making with the presence of rebate. As a numerical solution, the RL algorithm successfully mirrors the analytical solutions under the scheme of no rebate and constant rebate. Under the time-dependent rebate scheme, there is no closed form and RL provides a plausible solution. We investigate the numerical performance of the RL solutions in simulations, which show that the RL solutions deliver stable accuracy in various situations and are robust to estimation errors. Moreover, the RL solutions demonstrate the impact of rebate on the behaviour of market makers (MMs) and the quality of market. In particular, the presence of a rebate stimulates MM to quote with narrower spreads on both sides of order books and the rebate is fully transferred to the end customers, which is consistent with the theoretical results in the analytical solutions. It also improves market quality by increasing the total trading volume and providing more terminal wealth to MMs. Finally, the time-dependent rebate scheme is found to be more cost efficient than a constant rebate.
{"title":"Reinforcement Learning for Optimal Market Making with the Presence of Rebate","authors":"Ge Zhang, Ying Chen","doi":"10.2139/ssrn.3646753","DOIUrl":"https://doi.org/10.2139/ssrn.3646753","url":null,"abstract":"We propose a reinforcement learning (RL) framework to solve the HJB equations of optimal market making with the presence of rebate. As a numerical solution, the RL algorithm successfully mirrors the analytical solutions under the scheme of no rebate and constant rebate. Under the time-dependent rebate scheme, there is no closed form and RL provides a plausible solution. We investigate the numerical performance of the RL solutions in simulations, which show that the RL solutions deliver stable accuracy in various situations and are robust to estimation errors. Moreover, the RL solutions demonstrate the impact of rebate on the behaviour of market makers (MMs) and the quality of market. In particular, the presence of a rebate stimulates MM to quote with narrower spreads on both sides of order books and the rebate is fully transferred to the end customers, which is consistent with the theoretical results in the analytical solutions. It also improves market quality by increasing the total trading volume and providing more terminal wealth to MMs. Finally, the time-dependent rebate scheme is found to be more cost efficient than a constant rebate.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133425912","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}
Pub Date : 2020-06-30DOI: 10.34218/ijeet.11.4.2020.046
R Srivatsan Sharath Cherian Thomas, V. P, Ravi Kumar C. V
In this paper a novel system is proposed to monitor the health of industrial machines thus helping in their maintenance and early failure detection. This will help in prediction of when an industrial machine or its part will malfunction based on the data extracted from it. We will be able to replace the part or the machine in advance before any production lines get affected. This way resources will be saved and also cost of maintenance will be reduced. On top of this it is not possible to always manually monitor machines placed in remote areas like motors and pumps in water supply systems, sewage plants and chemical plants but our system would be able to not just monitor the machines but also predict the machine’s current health. The proposal encompasses a lightweight machine monitoring system for next generation M2M ecosystem for on the fly fault detection and diagnosis.
{"title":"Early Maintenance and Diagnosis of Connected Machines Using Machine Learning","authors":"R Srivatsan Sharath Cherian Thomas, V. P, Ravi Kumar C. V","doi":"10.34218/ijeet.11.4.2020.046","DOIUrl":"https://doi.org/10.34218/ijeet.11.4.2020.046","url":null,"abstract":"In this paper a novel system is proposed to monitor the health of industrial machines thus helping in their maintenance and early failure detection. This will help in prediction of when an industrial machine or its part will malfunction based on the data extracted from it. We will be able to replace the part or the machine in advance before any production lines get affected. This way resources will be saved and also cost of maintenance will be reduced. On top of this it is not possible to always manually monitor machines placed in remote areas like motors and pumps in water supply systems, sewage plants and chemical plants but our system would be able to not just monitor the machines but also predict the machine’s current health. The proposal encompasses a lightweight machine monitoring system for next generation M2M ecosystem for on the fly fault detection and diagnosis.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125274404","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：