The concept of time mostly plays a subordinate role in finance and economics. The assumption is that time flows continuously and that time series data should be analyzed at regular, equidistant intervals. Nonetheless, already nearly 60 years ago, the concept of an event-based measure of time was first introduced. This paper expands on this theme by discussing the paradigm of intrinsic time, its origins, history, and modern applications. Departing from traditional, continuous measures of time, intrinsic time proposes an event-based, algorithmic framework that captures the dynamic and fluctuating nature of real-world phenomena more accurately. Unsuspected implications arise in general for complex systems and specifically for financial markets. For instance, novel structures and regularities are revealed, otherwise obscured by any analysis utilizing equidistant time intervals. Of particular interest is the emergence of a multiplicity of scaling laws, a hallmark signature of an underlying organizational principle in complex systems. Moreover, a central insight from this novel paradigm is the realization that universal time does not exist; instead, time is observer-dependent, shaped by the intrinsic activity unfolding within complex systems. This research opens up new avenues for economic modeling and forecasting, paving the way for a deeper understanding of the invisible forces that guide the evolution and emergence of market dynamics and financial systems. An exciting and rich landscape of possibilities emerges within the paradigm of intrinsic time.
{"title":"The Theory of Intrinsic Time: A Primer","authors":"James B. Glattfelder, Richard B. Olsen","doi":"arxiv-2406.07354","DOIUrl":"https://doi.org/arxiv-2406.07354","url":null,"abstract":"The concept of time mostly plays a subordinate role in finance and economics.\u0000The assumption is that time flows continuously and that time series data should\u0000be analyzed at regular, equidistant intervals. Nonetheless, already nearly 60\u0000years ago, the concept of an event-based measure of time was first introduced.\u0000This paper expands on this theme by discussing the paradigm of intrinsic time,\u0000its origins, history, and modern applications. Departing from traditional,\u0000continuous measures of time, intrinsic time proposes an event-based,\u0000algorithmic framework that captures the dynamic and fluctuating nature of\u0000real-world phenomena more accurately. Unsuspected implications arise in general\u0000for complex systems and specifically for financial markets. For instance, novel\u0000structures and regularities are revealed, otherwise obscured by any analysis\u0000utilizing equidistant time intervals. Of particular interest is the emergence\u0000of a multiplicity of scaling laws, a hallmark signature of an underlying\u0000organizational principle in complex systems. Moreover, a central insight from\u0000this novel paradigm is the realization that universal time does not exist;\u0000instead, time is observer-dependent, shaped by the intrinsic activity unfolding\u0000within complex systems. This research opens up new avenues for economic\u0000modeling and forecasting, paving the way for a deeper understanding of the\u0000invisible forces that guide the evolution and emergence of market dynamics and\u0000financial systems. An exciting and rich landscape of possibilities emerges\u0000within the paradigm of intrinsic time.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141503473","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}
In this work we address the question of the Multifractal detrended cross-correlation analysis method that has been subject to some controversies since its inception almost two decades ago. To this end we propose several new options to deal with negative cross-covariance among two time series, that may serve to construct a more robust view of the multifractal spectrum among the series. We compare these novel options with the proposals already existing in the literature, and we provide fast code in C, R and Python for both new and the already existing proposals. We test different algorithms on synthetic series with an exact analytical solution, as well as on daily price series of ethanol and sugar in Brazil from 2010 to 2023.
{"title":"Dissecting Multifractal detrended cross-correlation analysis","authors":"Borko Stosic, Tatijana Stosic","doi":"arxiv-2406.19406","DOIUrl":"https://doi.org/arxiv-2406.19406","url":null,"abstract":"In this work we address the question of the Multifractal detrended\u0000cross-correlation analysis method that has been subject to some controversies\u0000since its inception almost two decades ago. To this end we propose several new\u0000options to deal with negative cross-covariance among two time series, that may\u0000serve to construct a more robust view of the multifractal spectrum among the\u0000series. We compare these novel options with the proposals already existing in\u0000the literature, and we provide fast code in C, R and Python for both new and\u0000the already existing proposals. We test different algorithms on synthetic\u0000series with an exact analytical solution, as well as on daily price series of\u0000ethanol and sugar in Brazil from 2010 to 2023.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141531113","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}
Cristiano Salvagnin, Aldo Glielmo, Maria Elena De Giuli, Antonietta Mira
The European carbon market plays a pivotal role in the European Union's ambitious target of achieving carbon neutrality by 2050. Understanding the intricacies of factors influencing European Union Emission Trading System (EU ETS) market prices is paramount for effective policy making and strategy implementation. We propose the use of the Information Imbalance, a recently introduced non-parametric measure quantifying the degree to which a set of variables is informative with respect to another one, to study the relationships among macroeconomic, economic, uncertainty, and energy variables concerning EU ETS prices. Our analysis shows that in Phase 3 commodity related variables such as the ERIX index are the most informative to explain the behaviour of the EU ETS market price. Transitioning to Phase 4, financial fluctuations take centre stage, with the uncertainty in the EUR/CHF exchange rate emerging as a crucial determinant. These results reflect the disruptive impacts of the COVID-19 pandemic and the energy crisis in reshaping the importance of the different variables. Beyond variable analysis, we also propose to leverage the Information Imbalance to address the problem of mixed-frequency forecasting, and we identify the weekly time scale as the most informative for predicting the EU ETS price. Finally, we show how the Information Imbalance can be effectively combined with Gaussian Process regression for efficient nowcasting and forecasting using very small sets of highly informative predictors.
{"title":"Investigating the price determinants of the European Emission Trading System: a non-parametric approach","authors":"Cristiano Salvagnin, Aldo Glielmo, Maria Elena De Giuli, Antonietta Mira","doi":"arxiv-2406.05094","DOIUrl":"https://doi.org/arxiv-2406.05094","url":null,"abstract":"The European carbon market plays a pivotal role in the European Union's\u0000ambitious target of achieving carbon neutrality by 2050. Understanding the\u0000intricacies of factors influencing European Union Emission Trading System (EU\u0000ETS) market prices is paramount for effective policy making and strategy\u0000implementation. We propose the use of the Information Imbalance, a recently\u0000introduced non-parametric measure quantifying the degree to which a set of\u0000variables is informative with respect to another one, to study the\u0000relationships among macroeconomic, economic, uncertainty, and energy variables\u0000concerning EU ETS prices. Our analysis shows that in Phase 3 commodity related\u0000variables such as the ERIX index are the most informative to explain the\u0000behaviour of the EU ETS market price. Transitioning to Phase 4, financial\u0000fluctuations take centre stage, with the uncertainty in the EUR/CHF exchange\u0000rate emerging as a crucial determinant. These results reflect the disruptive\u0000impacts of the COVID-19 pandemic and the energy crisis in reshaping the\u0000importance of the different variables. Beyond variable analysis, we also\u0000propose to leverage the Information Imbalance to address the problem of\u0000mixed-frequency forecasting, and we identify the weekly time scale as the most\u0000informative for predicting the EU ETS price. Finally, we show how the\u0000Information Imbalance can be effectively combined with Gaussian Process\u0000regression for efficient nowcasting and forecasting using very small sets of\u0000highly informative predictors.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141503475","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}
Wojciech Wisniewski, Yuri Kalnishkan, David Lindsay, Siân Lindsay
Financial organisations such as brokers face a significant challenge in servicing the investment needs of thousands of their traders worldwide. This task is further compounded since individual traders will have their own risk appetite and investment goals. Traders may look to capture short-term trends in the market which last only seconds to minutes, or they may have longer-term views which last several days to months. To reduce the complexity of this task, client trades can be clustered. By examining such clusters, we would likely observe many traders following common patterns of investment, but how do these patterns vary through time? Knowledge regarding the temporal distributions of such clusters may help financial institutions manage the overall portfolio of risk that accumulates from underlying trader positions. This study contributes to the field by demonstrating that the distribution of clusters derived from the real-world trades of 20k Foreign Exchange (FX) traders (from 2015 to 2017) is described in accordance with Ewens' Sampling Distribution. Further, we show that the Aggregating Algorithm (AA), an on-line prediction with expert advice algorithm, can be applied to the aforementioned real-world data in order to improve the returns of portfolios of trader risk. However we found that the AA 'struggles' when presented with too many trader ``experts'', especially when there are many trades with similar overall patterns. To help overcome this challenge, we have applied and compared the use of Statistically Validated Networks (SVN) with a hierarchical clustering approach on a subset of the data, demonstrating that both approaches can be used to significantly improve results of the AA in terms of profitability and smoothness of returns.
{"title":"Temporal distribution of clusters of investors and their application in prediction with expert advice","authors":"Wojciech Wisniewski, Yuri Kalnishkan, David Lindsay, Siân Lindsay","doi":"arxiv-2406.19403","DOIUrl":"https://doi.org/arxiv-2406.19403","url":null,"abstract":"Financial organisations such as brokers face a significant challenge in\u0000servicing the investment needs of thousands of their traders worldwide. This\u0000task is further compounded since individual traders will have their own risk\u0000appetite and investment goals. Traders may look to capture short-term trends in\u0000the market which last only seconds to minutes, or they may have longer-term\u0000views which last several days to months. To reduce the complexity of this task,\u0000client trades can be clustered. By examining such clusters, we would likely\u0000observe many traders following common patterns of investment, but how do these\u0000patterns vary through time? Knowledge regarding the temporal distributions of\u0000such clusters may help financial institutions manage the overall portfolio of\u0000risk that accumulates from underlying trader positions. This study contributes\u0000to the field by demonstrating that the distribution of clusters derived from\u0000the real-world trades of 20k Foreign Exchange (FX) traders (from 2015 to 2017)\u0000is described in accordance with Ewens' Sampling Distribution. Further, we show\u0000that the Aggregating Algorithm (AA), an on-line prediction with expert advice\u0000algorithm, can be applied to the aforementioned real-world data in order to\u0000improve the returns of portfolios of trader risk. However we found that the AA\u0000'struggles' when presented with too many trader ``experts'', especially when\u0000there are many trades with similar overall patterns. To help overcome this\u0000challenge, we have applied and compared the use of Statistically Validated\u0000Networks (SVN) with a hierarchical clustering approach on a subset of the data,\u0000demonstrating that both approaches can be used to significantly improve results\u0000of the AA in terms of profitability and smoothness of returns.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141516803","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}
Stochastic differential equation (SDE) models are the foundation for pricing and hedging financial derivatives. The drift and volatility functions in SDE models are typically chosen to be algebraic functions with a small number (less than 5) parameters which can be calibrated to market data. A more flexible approach is to use neural networks to model the drift and volatility functions, which provides more degrees-of-freedom to match observed market data. Training of models requires optimizing over an SDE, which is computationally challenging. For European options, we develop a fast stochastic gradient descent (SGD) algorithm for training the neural network-SDE model. Our SGD algorithm uses two independent SDE paths to obtain an unbiased estimate of the direction of steepest descent. For American options, we optimize over the corresponding Kolmogorov partial differential equation (PDE). The neural network appears as coefficient functions in the PDE. Models are trained on large datasets (many contracts), requiring either large simulations (many Monte Carlo samples for the stock price paths) or large numbers of PDEs (a PDE must be solved for each contract). Numerical results are presented for real market data including S&P 500 index options, S&P 100 index options, and single-stock American options. The neural-network-based SDE models are compared against the Black-Scholes model, the Dupire's local volatility model, and the Heston model. Models are evaluated in terms of how accurate they are at pricing out-of-sample financial derivatives, which is a core task in derivative pricing at financial institutions.
{"title":"Machine Learning Methods for Pricing Financial Derivatives","authors":"Lei Fan, Justin Sirignano","doi":"arxiv-2406.00459","DOIUrl":"https://doi.org/arxiv-2406.00459","url":null,"abstract":"Stochastic differential equation (SDE) models are the foundation for pricing\u0000and hedging financial derivatives. The drift and volatility functions in SDE\u0000models are typically chosen to be algebraic functions with a small number (less\u0000than 5) parameters which can be calibrated to market data. A more flexible\u0000approach is to use neural networks to model the drift and volatility functions,\u0000which provides more degrees-of-freedom to match observed market data. Training\u0000of models requires optimizing over an SDE, which is computationally\u0000challenging. For European options, we develop a fast stochastic gradient\u0000descent (SGD) algorithm for training the neural network-SDE model. Our SGD\u0000algorithm uses two independent SDE paths to obtain an unbiased estimate of the\u0000direction of steepest descent. For American options, we optimize over the\u0000corresponding Kolmogorov partial differential equation (PDE). The neural\u0000network appears as coefficient functions in the PDE. Models are trained on\u0000large datasets (many contracts), requiring either large simulations (many Monte\u0000Carlo samples for the stock price paths) or large numbers of PDEs (a PDE must\u0000be solved for each contract). Numerical results are presented for real market\u0000data including S&P 500 index options, S&P 100 index options, and single-stock\u0000American options. The neural-network-based SDE models are compared against the\u0000Black-Scholes model, the Dupire's local volatility model, and the Heston model.\u0000Models are evaluated in terms of how accurate they are at pricing out-of-sample\u0000financial derivatives, which is a core task in derivative pricing at financial\u0000institutions.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141258807","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 employs Topological Data Analysis (TDA) to detect extreme events (EEs) in the stock market at a continental level. Previous approaches, which analyzed stock indices separately, could not detect EEs for multiple time series in one go. TDA provides a robust framework for such analysis and identifies the EEs during the crashes for different indices. The TDA analysis shows that $L^1$, $L^2$ norms and Wasserstein distance ($W_D$) of the world leading indices rise abruptly during the crashes, surpassing a threshold of $mu+4*sigma$ where $mu$ and $sigma$ are the mean and the standard deviation of norm or $W_D$, respectively. Our study identified the stock index crashes of the 2008 financial crisis and the COVID-19 pandemic across continents as EEs. Given that different sectors in an index behave differently, a sector-wise analysis was conducted during the COVID-19 pandemic for the Indian stock market. The sector-wise results show that after the occurrence of EE, we have observed strong crashes surpassing $mu+2*sigma$ for an extended period for the banking sector. While for the pharmaceutical sector, no significant spikes were noted. Hence, TDA also proves successful in identifying the duration of shocks after the occurrence of EEs. This also indicates that the Banking sector continued to face stress and remained volatile even after the crash. This study gives us the applicability of TDA as a powerful analytical tool to study EEs in various fields.
{"title":"Identifying Extreme Events in the Stock Market: A Topological Data Analysis","authors":"Anish Rai, Buddha Nath Sharma, Salam Rabindrajit Luwang, Md. Nurujjaman, Sushovan Majhi","doi":"arxiv-2405.16052","DOIUrl":"https://doi.org/arxiv-2405.16052","url":null,"abstract":"This paper employs Topological Data Analysis (TDA) to detect extreme events\u0000(EEs) in the stock market at a continental level. Previous approaches, which\u0000analyzed stock indices separately, could not detect EEs for multiple time\u0000series in one go. TDA provides a robust framework for such analysis and\u0000identifies the EEs during the crashes for different indices. The TDA analysis\u0000shows that $L^1$, $L^2$ norms and Wasserstein distance ($W_D$) of the world\u0000leading indices rise abruptly during the crashes, surpassing a threshold of\u0000$mu+4*sigma$ where $mu$ and $sigma$ are the mean and the standard deviation\u0000of norm or $W_D$, respectively. Our study identified the stock index crashes of\u0000the 2008 financial crisis and the COVID-19 pandemic across continents as EEs.\u0000Given that different sectors in an index behave differently, a sector-wise\u0000analysis was conducted during the COVID-19 pandemic for the Indian stock\u0000market. The sector-wise results show that after the occurrence of EE, we have\u0000observed strong crashes surpassing $mu+2*sigma$ for an extended period for\u0000the banking sector. While for the pharmaceutical sector, no significant spikes\u0000were noted. Hence, TDA also proves successful in identifying the duration of\u0000shocks after the occurrence of EEs. This also indicates that the Banking sector\u0000continued to face stress and remained volatile even after the crash. This study\u0000gives us the applicability of TDA as a powerful analytical tool to study EEs in\u0000various fields.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"2016 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141166369","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}
The study examines whether broader market factors and the Fama-French three-factor model can effectively analyze the idiosyncratic risk and return characteristics of Bitcoin. By incorporating Fama-french factors, the explanatory power of these factors on Bitcoin's excess returns over various moving average periods is tested. The analysis aims to determine if equity market factors are significant in explaining and modeling systemic risk in Bitcoin.
{"title":"An empirical study of market risk factors for Bitcoin","authors":"Shubham Singh","doi":"arxiv-2406.19401","DOIUrl":"https://doi.org/arxiv-2406.19401","url":null,"abstract":"The study examines whether broader market factors and the Fama-French\u0000three-factor model can effectively analyze the idiosyncratic risk and return\u0000characteristics of Bitcoin. By incorporating Fama-french factors, the\u0000explanatory power of these factors on Bitcoin's excess returns over various\u0000moving average periods is tested. The analysis aims to determine if equity\u0000market factors are significant in explaining and modeling systemic risk in\u0000Bitcoin.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"51 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141516804","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 research paper aims to investigate the efficacy of decision trees in constructing intraday trading strategies using existing technical indicators for individual equities in the NIFTY50 index. Unlike conventional methods that rely on a fixed set of rules based on combinations of technical indicators developed by a human trader through their analysis, the proposed approach leverages decision trees to create unique trading rules for each stock, potentially enhancing trading performance and saving time. By extensively backtesting the strategy for each stock, a trader can determine whether to employ the rules generated by the decision tree for that specific stock. While this method does not guarantee success for every stock, decision treebased strategies outperform the simple buy-and-hold strategy for many stocks. The results highlight the proficiency of decision trees as a valuable tool for enhancing intraday trading performance on a stock-by-stock basis and could be of interest to traders seeking to improve their trading strategies.
{"title":"Decision Trees for Intuitive Intraday Trading Strategies","authors":"Prajwal Naga, Dinesh Balivada, Sharath Chandra Nirmala, Poornoday Tiruveedi","doi":"arxiv-2405.13959","DOIUrl":"https://doi.org/arxiv-2405.13959","url":null,"abstract":"This research paper aims to investigate the efficacy of decision trees in\u0000constructing intraday trading strategies using existing technical indicators\u0000for individual equities in the NIFTY50 index. Unlike conventional methods that\u0000rely on a fixed set of rules based on combinations of technical indicators\u0000developed by a human trader through their analysis, the proposed approach\u0000leverages decision trees to create unique trading rules for each stock,\u0000potentially enhancing trading performance and saving time. By extensively\u0000backtesting the strategy for each stock, a trader can determine whether to\u0000employ the rules generated by the decision tree for that specific stock. While\u0000this method does not guarantee success for every stock, decision treebased\u0000strategies outperform the simple buy-and-hold strategy for many stocks. The\u0000results highlight the proficiency of decision trees as a valuable tool for\u0000enhancing intraday trading performance on a stock-by-stock basis and could be\u0000of interest to traders seeking to improve their trading strategies.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141149325","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}
Andrew Estornell, Stylianos Loukas Vasileiou, William Yeoh, Daniel Borrajo, Rui Silva
In today's competitive financial landscape, understanding and anticipating customer goals is crucial for institutions to deliver a personalized and optimized user experience. This has given rise to the problem of accurately predicting customer goals and actions. Focusing on that problem, we use historical customer traces generated by a realistic simulator and present two simple models for predicting customer goals and future actions -- an LSTM model and an LSTM model enhanced with state-space graph embeddings. Our results demonstrate the effectiveness of these models when it comes to predicting customer goals and actions.
{"title":"Predicting Customer Goals in Financial Institution Services: A Data-Driven LSTM Approach","authors":"Andrew Estornell, Stylianos Loukas Vasileiou, William Yeoh, Daniel Borrajo, Rui Silva","doi":"arxiv-2406.19399","DOIUrl":"https://doi.org/arxiv-2406.19399","url":null,"abstract":"In today's competitive financial landscape, understanding and anticipating\u0000customer goals is crucial for institutions to deliver a personalized and\u0000optimized user experience. This has given rise to the problem of accurately\u0000predicting customer goals and actions. Focusing on that problem, we use\u0000historical customer traces generated by a realistic simulator and present two\u0000simple models for predicting customer goals and future actions -- an LSTM model\u0000and an LSTM model enhanced with state-space graph embeddings. Our results\u0000demonstrate the effectiveness of these models when it comes to predicting\u0000customer goals and actions.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141531114","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}
Jinxin Xu, Kaixian Xu, Yue Wang, Qinyan Shen, Ruisi Li
Financial market risk forecasting involves applying mathematical models, historical data analysis and statistical methods to estimate the impact of future market movements on investments. This process is crucial for investors to develop strategies, financial institutions to manage assets and regulators to formulate policy. In today's society, there are problems of high error rate and low precision in financial market risk prediction, which greatly affect the accuracy of financial market risk prediction. K-means algorithm in machine learning is an effective risk prediction technique for financial market. This study uses K-means algorithm to develop a financial market risk prediction system, which significantly improves the accuracy and efficiency of financial market risk prediction. Ultimately, the outcomes of the experiments confirm that the K-means algorithm operates with user-friendly simplicity and achieves a 94.61% accuracy rate
{"title":"A K-means Algorithm for Financial Market Risk Forecasting","authors":"Jinxin Xu, Kaixian Xu, Yue Wang, Qinyan Shen, Ruisi Li","doi":"arxiv-2405.13076","DOIUrl":"https://doi.org/arxiv-2405.13076","url":null,"abstract":"Financial market risk forecasting involves applying mathematical models,\u0000historical data analysis and statistical methods to estimate the impact of\u0000future market movements on investments. This process is crucial for investors\u0000to develop strategies, financial institutions to manage assets and regulators\u0000to formulate policy. In today's society, there are problems of high error rate\u0000and low precision in financial market risk prediction, which greatly affect the\u0000accuracy of financial market risk prediction. K-means algorithm in machine\u0000learning is an effective risk prediction technique for financial market. This\u0000study uses K-means algorithm to develop a financial market risk prediction\u0000system, which significantly improves the accuracy and efficiency of financial\u0000market risk prediction. Ultimately, the outcomes of the experiments confirm\u0000that the K-means algorithm operates with user-friendly simplicity and achieves\u0000a 94.61% accuracy rate","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141149264","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：