{
  "id": 284909,
  "title": "Papers on Crypto trading",
  "url": "/competitions/g-research-crypto-forecasting/discussion/284909",
  "author_name": "Charlie Craine",
  "post_date": "2021-11-02T20:19:39.412000",
  "votes": 109,
  "comment_count": 10,
  "views": 0,
  "content": "<p>Hey everyone!</p>\n<p>I wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!</p>\n<p><strong>Research Papers:</strong></p>\n<ul>\n<li><p><a href=\"https://arxiv.org/abs/2109.14789\" target=\"_blank\">Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning</a> - The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. </p></li>\n<li><p><a href=\"https://arxiv.org/abs/2102.08189\" target=\"_blank\">On Technical Trading and Social Media Indicators in Cryptocurrencies' Price Classification Through Deep Learning</a> - This work aims to analyse the predictability of price movements of cryptocurrencies on both hourly and daily data observed from January 2017 to January 2021, using deep learning algorithms. For our experiments, we used three sets of features: technical, trading and social media indicators, considering a restricted model of only technical indicators and an unrestricted model with technical, trading and social media indicators. We verified whether the consideration of trading and social media indicators, along with the classic technical variables (such as price's returns), leads to a significative improvement in the prediction of cryptocurrencies price's changes.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2101.09738\" target=\"_blank\">Currency Network Risk</a> - This paper identifies new currency risk stemming from a network of idiosyncratic option-based currency volatilities and shows how such network risk is priced in the cross-section of currency returns. A portfolio that buys net-receivers and sells net-transmitters of short-term linkages between currency volatilities generates a significant Sharpe ratio. The network strategy formed on causal connections is uncorrelated with popular benchmarks and generates a significant alpha, while network returns formed on aggregate connections, which are driven by a strong correlation component, are partially subsumed by standard factors. Long-term linkages are priced less, indicating a downward-sloping term structure of network risk.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2110.09429\" target=\"_blank\">Understanding jumps in high frequency digital asset markets</a> - While attention is a predictor for digital asset prices, and jumps in Bitcoin prices are well-known, we know little about its alternatives. Studying high frequency crypto data gives us the unique possibility to confirm that cross market digital asset returns are driven by high frequency jumps clustered around black swan events, resembling volatility and trading volume seasonalities. Regressions show that intra-day jumps significantly influence end of day returns in size and direction. This provides fundamental research for crypto option pricing models. However, we need better econometric methods for capturing the specific market microstructure of cryptos.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2109.11270\" target=\"_blank\">Towards Private On-Chain Algorithmic Trading</a> - We show how to partition the computation into on- and off-chain components in a way that provides a measure of end-to-end integrity, while preserving the algorithmic \"secret sauce\". Our system is enabled with a careful use of algorithm partitioning, zero-knowledge proofs and smart contracts. We also show that with layer-2 (L2) technologies, trades can be kept private, which means that algorithmic parameters are difficult to recover by a chain observer. </p></li>\n<li><p><a href=\"https://arxiv.org/abs/2108.11921\" target=\"_blank\">A Time-Varying Network for Cryptocurrencies</a> - Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities. We develop a dynamic covariate-assisted spectral clustering method to consistently estimate the latent community structure of cryptocurrencies network that accounts for both sets of information. We demonstrate that investors can achieve better risk diversification by investing in cryptocurrencies from different communities. A cross-sectional portfolio that implements an inter-crypto momentum trading strategy earns a 1.08% daily return. By dissecting the portfolio returns on behavioral factors, we confirm that our results are not driven by behavioral mechanisms.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2003.11352\" target=\"_blank\">Cryptocurrency Trading: A Comprehensive Survey</a> - In recent years, the tendency of the number of financial institutions including cryptocurrencies in their portfolios has accelerated. Cryptocurrencies are the first pure digital assets to be included by asset managers. Although they have some commonalities with more traditional assets, they have their own separate nature and their behaviour as an asset is still in the process of being understood. It is therefore important to summarise existing research papers and results on cryptocurrency trading, including available trading platforms, trading signals, trading strategy research and risk management. This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading (e.g., cryptocurrency trading systems, bubble and extreme conditions, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others). This paper also analyses datasets, research trends and distribution among research objects(contents/properties) and technologies, concluding with some promising opportunities that remain open in cryptocurrency trading.</p></li>\n</ul>",
  "messages": [
    {
      "id": 1568526,
      "postDate": "2021-11-02T20:19:39.413Z",
      "content": "<p>Hey everyone!</p>\n<p>I wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!</p>\n<p><strong>Research Papers:</strong></p>\n<ul>\n<li><p><a href=\"https://arxiv.org/abs/2109.14789\" target=\"_blank\">Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning</a> - The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. </p></li>\n<li><p><a href=\"https://arxiv.org/abs/2102.08189\" target=\"_blank\">On Technical Trading and Social Media Indicators in Cryptocurrencies' Price Classification Through Deep Learning</a> - This work aims to analyse the predictability of price movements of cryptocurrencies on both hourly and daily data observed from January 2017 to January 2021, using deep learning algorithms. For our experiments, we used three sets of features: technical, trading and social media indicators, considering a restricted model of only technical indicators and an unrestricted model with technical, trading and social media indicators. We verified whether the consideration of trading and social media indicators, along with the classic technical variables (such as price's returns), leads to a significative improvement in the prediction of cryptocurrencies price's changes.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2101.09738\" target=\"_blank\">Currency Network Risk</a> - This paper identifies new currency risk stemming from a network of idiosyncratic option-based currency volatilities and shows how such network risk is priced in the cross-section of currency returns. A portfolio that buys net-receivers and sells net-transmitters of short-term linkages between currency volatilities generates a significant Sharpe ratio. The network strategy formed on causal connections is uncorrelated with popular benchmarks and generates a significant alpha, while network returns formed on aggregate connections, which are driven by a strong correlation component, are partially subsumed by standard factors. Long-term linkages are priced less, indicating a downward-sloping term structure of network risk.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2110.09429\" target=\"_blank\">Understanding jumps in high frequency digital asset markets</a> - While attention is a predictor for digital asset prices, and jumps in Bitcoin prices are well-known, we know little about its alternatives. Studying high frequency crypto data gives us the unique possibility to confirm that cross market digital asset returns are driven by high frequency jumps clustered around black swan events, resembling volatility and trading volume seasonalities. Regressions show that intra-day jumps significantly influence end of day returns in size and direction. This provides fundamental research for crypto option pricing models. However, we need better econometric methods for capturing the specific market microstructure of cryptos.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2109.11270\" target=\"_blank\">Towards Private On-Chain Algorithmic Trading</a> - We show how to partition the computation into on- and off-chain components in a way that provides a measure of end-to-end integrity, while preserving the algorithmic \"secret sauce\". Our system is enabled with a careful use of algorithm partitioning, zero-knowledge proofs and smart contracts. We also show that with layer-2 (L2) technologies, trades can be kept private, which means that algorithmic parameters are difficult to recover by a chain observer. </p></li>\n<li><p><a href=\"https://arxiv.org/abs/2108.11921\" target=\"_blank\">A Time-Varying Network for Cryptocurrencies</a> - Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities. We develop a dynamic covariate-assisted spectral clustering method to consistently estimate the latent community structure of cryptocurrencies network that accounts for both sets of information. We demonstrate that investors can achieve better risk diversification by investing in cryptocurrencies from different communities. A cross-sectional portfolio that implements an inter-crypto momentum trading strategy earns a 1.08% daily return. By dissecting the portfolio returns on behavioral factors, we confirm that our results are not driven by behavioral mechanisms.</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2003.11352\" target=\"_blank\">Cryptocurrency Trading: A Comprehensive Survey</a> - In recent years, the tendency of the number of financial institutions including cryptocurrencies in their portfolios has accelerated. Cryptocurrencies are the first pure digital assets to be included by asset managers. Although they have some commonalities with more traditional assets, they have their own separate nature and their behaviour as an asset is still in the process of being understood. It is therefore important to summarise existing research papers and results on cryptocurrency trading, including available trading platforms, trading signals, trading strategy research and risk management. This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading (e.g., cryptocurrency trading systems, bubble and extreme conditions, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others). This paper also analyses datasets, research trends and distribution among research objects(contents/properties) and technologies, concluding with some promising opportunities that remain open in cryptocurrency trading.</p></li>\n</ul>",
      "rawMarkdown": "Hey everyone!\n\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\n**Research Papers:**\n\n- [Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning](https://arxiv.org/abs/2109.14789) - The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. \n\n- [On Technical Trading and Social Media Indicators in Cryptocurrencies' Price Classification Through Deep Learning](https://arxiv.org/abs/2102.08189) - This work aims to analyse the predictability of price movements of cryptocurrencies on both hourly and daily data observed from January 2017 to January 2021, using deep learning algorithms. For our experiments, we used three sets of features: technical, trading and social media indicators, considering a restricted model of only technical indicators and an unrestricted model with technical, trading and social media indicators. We verified whether the consideration of trading and social media indicators, along with the classic technical variables (such as price's returns), leads to a significative improvement in the prediction of cryptocurrencies price's changes.\n\n- [Currency Network Risk](https://arxiv.org/abs/2101.09738) - This paper identifies new currency risk stemming from a network of idiosyncratic option-based currency volatilities and shows how such network risk is priced in the cross-section of currency returns. A portfolio that buys net-receivers and sells net-transmitters of short-term linkages between currency volatilities generates a significant Sharpe ratio. The network strategy formed on causal connections is uncorrelated with popular benchmarks and generates a significant alpha, while network returns formed on aggregate connections, which are driven by a strong correlation component, are partially subsumed by standard factors. Long-term linkages are priced less, indicating a downward-sloping term structure of network risk.\n\n- [Understanding jumps in high frequency digital asset markets](https://arxiv.org/abs/2110.09429) - While attention is a predictor for digital asset prices, and jumps in Bitcoin prices are well-known, we know little about its alternatives. Studying high frequency crypto data gives us the unique possibility to confirm that cross market digital asset returns are driven by high frequency jumps clustered around black swan events, resembling volatility and trading volume seasonalities. Regressions show that intra-day jumps significantly influence end of day returns in size and direction. This provides fundamental research for crypto option pricing models. However, we need better econometric methods for capturing the specific market microstructure of cryptos.\n\n- [Towards Private On-Chain Algorithmic Trading](https://arxiv.org/abs/2109.11270) - We show how to partition the computation into on- and off-chain components in a way that provides a measure of end-to-end integrity, while preserving the algorithmic \"secret sauce\". Our system is enabled with a careful use of algorithm partitioning, zero-knowledge proofs and smart contracts. We also show that with layer-2 (L2) technologies, trades can be kept private, which means that algorithmic parameters are difficult to recover by a chain observer. \n\n- [A Time-Varying Network for Cryptocurrencies](https://arxiv.org/abs/2108.11921) - Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities. We develop a dynamic covariate-assisted spectral clustering method to consistently estimate the latent community structure of cryptocurrencies network that accounts for both sets of information. We demonstrate that investors can achieve better risk diversification by investing in cryptocurrencies from different communities. A cross-sectional portfolio that implements an inter-crypto momentum trading strategy earns a 1.08% daily return. By dissecting the portfolio returns on behavioral factors, we confirm that our results are not driven by behavioral mechanisms.\n\n- [Cryptocurrency Trading: A Comprehensive Survey](https://arxiv.org/abs/2003.11352) - In recent years, the tendency of the number of financial institutions including cryptocurrencies in their portfolios has accelerated. Cryptocurrencies are the first pure digital assets to be included by asset managers. Although they have some commonalities with more traditional assets, they have their own separate nature and their behaviour as an asset is still in the process of being understood. It is therefore important to summarise existing research papers and results on cryptocurrency trading, including available trading platforms, trading signals, trading strategy research and risk management. This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading (e.g., cryptocurrency trading systems, bubble and extreme conditions, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others). This paper also analyses datasets, research trends and distribution among research objects(contents/properties) and technologies, concluding with some promising opportunities that remain open in cryptocurrency trading.",
      "votes": 109
    },
    {
      "id": 1586275,
      "postDate": "2021-11-18T00:37:55.010Z",
      "content": "<p>You can find more <strong>IEEE</strong> standard papers<br>\n<a href=\"https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&amp;queryText=cryptocurrencies%20prediction\" target=\"_blank\">https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&amp;queryText=cryptocurrencies%20prediction</a></p>",
      "rawMarkdown": "You can find more **IEEE** standard papers\nhttps://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=cryptocurrencies%20prediction",
      "votes": 1
    },
    {
      "id": 1769340,
      "postDate": "2022-04-27T07:00:00.120Z",
      "content": "<p>Thx for sharing</p>",
      "rawMarkdown": "Thx for sharing"
    },
    {
      "id": 1635986,
      "postDate": "2022-01-02T13:25:37.467Z",
      "content": "<p>Great learning Resources.<br>\nThanks for sharing <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> </p>",
      "rawMarkdown": "Great learning Resources.\nThanks for sharing @crained "
    },
    {
      "id": 1587976,
      "postDate": "2021-11-19T05:13:51.810Z",
      "content": "<p>Can anyone please tell me what the \"count\" column is in the train.csv dataset?</p>",
      "rawMarkdown": "Can anyone please tell me what the \"count\" column is in the train.csv dataset?",
      "replies": [
        {
          "id": 1597850,
          "postDate": "2021-11-28T01:57:56.510Z",
          "content": "<p>The number of transactions for that coin in that minute.  All the columns are explained in the Data section</p>",
          "rawMarkdown": "The number of transactions for that coin in that minute.  All the columns are explained in the Data section"
        }
      ]
    },
    {
      "id": 1582534,
      "postDate": "2021-11-15T01:55:23.613Z",
      "content": "<p>Thanks for the information, I will be reading to understand better some options for modeling</p>",
      "rawMarkdown": "Thanks for the information, I will be reading to understand better some options for modeling"
    },
    {
      "id": 1568799,
      "postDate": "2021-11-03T03:32:08.100Z",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> for putting it together. Very helpful!</p>",
      "rawMarkdown": "Thank you @crained for putting it together. Very helpful!"
    },
    {
      "id": 1568534,
      "postDate": "2021-11-02T20:30:32.977Z",
      "content": "<p>These are some great references! </p>",
      "rawMarkdown": "These are some great references! "
    },
    {
      "id": 1570804,
      "postDate": "2021-11-04T11:40:54.903Z",
      "rawMarkdown": "",
      "votes": 6,
      "isDeleted": true,
      "replies": [
        {
          "id": 1635395,
          "postDate": "2022-01-01T18:07:49.897Z",
          "content": "<p>you delete this paper</p>",
          "rawMarkdown": "you delete this paper"
        }
      ]
    }
  ],
  "comments": [
    {
      "id": 1586275,
      "author_name": "laxman kusuma",
      "author_url": "",
      "post_date": "2021-11-18T00:37:55.010000",
      "content": "<p>You can find more <strong>IEEE</strong> standard papers<br>\n<a href=\"https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&amp;queryText=cryptocurrencies%20prediction\" target=\"_blank\">https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&amp;queryText=cryptocurrencies%20prediction</a></p>",
      "votes": 1,
      "replies": []
    },
    {
      "id": 1769340,
      "author_name": "MeijinLi",
      "author_url": "",
      "post_date": "2022-04-27T07:00:00.120000",
      "content": "<p>Thx for sharing</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1635986,
      "author_name": "arpan129",
      "author_url": "",
      "post_date": "2022-01-02T13:25:37.467000",
      "content": "<p>Great learning Resources.<br>\nThanks for sharing <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> </p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1587976,
      "author_name": "Aakash Chakraborty",
      "author_url": "",
      "post_date": "2021-11-19T05:13:51.810000",
      "content": "<p>Can anyone please tell me what the \"count\" column is in the train.csv dataset?</p>",
      "votes": 0,
      "replies": [
        {
          "id": 1597850,
          "author_name": "Kyle Peters",
          "author_url": "",
          "post_date": "2021-11-28T01:57:56.510000",
          "content": "<p>The number of transactions for that coin in that minute.  All the columns are explained in the Data section</p>",
          "votes": 0,
          "replies": []
        }
      ]
    },
    {
      "id": 1582534,
      "author_name": "C4rl05/V",
      "author_url": "",
      "post_date": "2021-11-15T01:55:23.613000",
      "content": "<p>Thanks for the information, I will be reading to understand better some options for modeling</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1568799,
      "author_name": "SRK",
      "author_url": "",
      "post_date": "2021-11-03T03:32:08.100000",
      "content": "<p>Thank you <a href=\"https://www.kaggle.com/crained\" target=\"_blank\">@crained</a> for putting it together. Very helpful!</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1568534,
      "author_name": "",
      "author_url": "",
      "post_date": "2021-11-02T20:30:32.977000",
      "content": "<p>These are some great references! </p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 1570804,
      "author_name": "",
      "author_url": "",
      "post_date": "2021-11-04T11:40:54.903000",
      "content": "",
      "votes": 6,
      "replies": [
        {
          "id": 1635395,
          "author_name": "Vladimir Shebunyaev",
          "author_url": "",
          "post_date": "2022-01-01T18:07:49.897000",
          "content": "<p>you delete this paper</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1568526": "Hey everyone!\n\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\n**Research Papers:**\n\n- [Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning](https://arxiv.org/abs/2109.14789) - The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. \n\n- [On Technical Trading and Social Media Indicators in Cryptocurrencies' Price Classification Through Deep Learning](https://arxiv.org/abs/2102.08189) - This work aims to analyse the predictability of price movements of cryptocurrencies on both hourly and daily data observed from January 2017 to January 2021, using deep learning algorithms. For our experiments, we used three sets of features: technical, trading and social media indicators, considering a restricted model of only technical indicators and an unrestricted model with technical, trading and social media indicators. We verified whether the consideration of trading and social media indicators, along with the classic technical variables (such as price's returns), leads to a significative improvement in the prediction of cryptocurrencies price's changes.\n\n- [Currency Network Risk](https://arxiv.org/abs/2101.09738) - This paper identifies new currency risk stemming from a network of idiosyncratic option-based currency volatilities and shows how such network risk is priced in the cross-section of currency returns. A portfolio that buys net-receivers and sells net-transmitters of short-term linkages between currency volatilities generates a significant Sharpe ratio. The network strategy formed on causal connections is uncorrelated with popular benchmarks and generates a significant alpha, while network returns formed on aggregate connections, which are driven by a strong correlation component, are partially subsumed by standard factors. Long-term linkages are priced less, indicating a downward-sloping term structure of network risk.\n\n- [Understanding jumps in high frequency digital asset markets](https://arxiv.org/abs/2110.09429) - While attention is a predictor for digital asset prices, and jumps in Bitcoin prices are well-known, we know little about its alternatives. Studying high frequency crypto data gives us the unique possibility to confirm that cross market digital asset returns are driven by high frequency jumps clustered around black swan events, resembling volatility and trading volume seasonalities. Regressions show that intra-day jumps significantly influence end of day returns in size and direction. This provides fundamental research for crypto option pricing models. However, we need better econometric methods for capturing the specific market microstructure of cryptos.\n\n- [Towards Private On-Chain Algorithmic Trading](https://arxiv.org/abs/2109.11270) - We show how to partition the computation into on- and off-chain components in a way that provides a measure of end-to-end integrity, while preserving the algorithmic \"secret sauce\". Our system is enabled with a careful use of algorithm partitioning, zero-knowledge proofs and smart contracts. We also show that with layer-2 (L2) technologies, trades can be kept private, which means that algorithmic parameters are difficult to recover by a chain observer. \n\n- [A Time-Varying Network for Cryptocurrencies](https://arxiv.org/abs/2108.11921) - Cryptocurrencies return cross-predictability and technological similarity yield information on risk propagation and market segmentation. To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities. We develop a dynamic covariate-assisted spectral clustering method to consistently estimate the latent community structure of cryptocurrencies network that accounts for both sets of information. We demonstrate that investors can achieve better risk diversification by investing in cryptocurrencies from different communities. A cross-sectional portfolio that implements an inter-crypto momentum trading strategy earns a 1.08% daily return. By dissecting the portfolio returns on behavioral factors, we confirm that our results are not driven by behavioral mechanisms.\n\n- [Cryptocurrency Trading: A Comprehensive Survey](https://arxiv.org/abs/2003.11352) - In recent years, the tendency of the number of financial institutions including cryptocurrencies in their portfolios has accelerated. Cryptocurrencies are the first pure digital assets to be included by asset managers. Although they have some commonalities with more traditional assets, they have their own separate nature and their behaviour as an asset is still in the process of being understood. It is therefore important to summarise existing research papers and results on cryptocurrency trading, including available trading platforms, trading signals, trading strategy research and risk management. This paper provides a comprehensive survey of cryptocurrency trading research, by covering 146 research papers on various aspects of cryptocurrency trading (e.g., cryptocurrency trading systems, bubble and extreme conditions, prediction of volatility and return, crypto-assets portfolio construction and crypto-assets, technical trading and others). This paper also analyses datasets, research trends and distribution among research objects(contents/properties) and technologies, concluding with some promising opportunities that remain open in cryptocurrency trading.",
    "1586275": "You can find more **IEEE** standard papers\nhttps://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=cryptocurrencies%20prediction",
    "1769340": "Thx for sharing",
    "1635986": "Great learning Resources.\nThanks for sharing @crained ",
    "1587976": "Can anyone please tell me what the \"count\" column is in the train.csv dataset?",
    "1582534": "Thanks for the information, I will be reading to understand better some options for modeling",
    "1568799": "Thank you @crained for putting it together. Very helpful!",
    "1568534": "These are some great references! ",
    "1570804": ""
  }
}