Dreaming machine learning: Lipschitz extensions for reinforcement learning on financial markets

Calabuig, J. M.; Falciani, H.; Pérez, Enrique Alfonso Sánchez

doi:10.1016/j.neucom.2020.02.052

Cited by 24 publications

(14 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It suggests a unique strategy for anomaly identification in high-performance computing systems based on a machine (deep) learning technology, namely, a type of neural network called an autoencoder. Using certain known states of the dynamical system that describes the evolution of the financial market [7], it simulates new states by interpolating genuine states and introducing some random variables. DeepBreath, a deep reinforcement learning framework, is used to create a portfolio management system [8,9].…”

Section: Related Workmentioning

confidence: 99%

Financial Abnormal Data Detection System Based on Reinforcement Learning

Hou

2022

Mobile Information Systems

View full text Add to dashboard Cite

The fraud of financial data has seriously damaged the interests of stakeholders and hindered the healthy development of the economy. Based on the reinforcement learning theory, this paper proposes a model of intelligent analysis of enterprise financial data anomalies, constructs the difference method, and transforms nontemporal indicators into temporal indicators. The proposed model uses a convolution neural network with four hidden layers to classify, evaluate, and analyze the constructed temporal indicators of financial data. The main objective is a more effective and accurate identification of the issue. The test results show that the intelligent analysis method of financial abnormal data based on deep learning has ideal effectiveness and accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Financial Abnormal Data Detection System Based on Reinforcement Learning

Hou

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…The second-named author was supported by the Priority Research Area SciMat under the program Excellence Initiative -Research University at the Jagiellonian University in Kraków. psychology ( p < 1) [27,36], the Zolotarev distance in spaces of random variables [40], and the d -distance in machine learning [13]. The terminology has not yet stabilized within the many generalizations of metric spaces and therefore let us determine which one we will work with here.…”

Section: Introductionmentioning

confidence: 99%

On a Family of Quasimetric Spaces in Generalized Potential Theory

Åhag

Czyż

2022

J Geom Anal

View full text Add to dashboard Cite

We construct a family of quasimetric spaces in generalized potential theory containing m-subharmonic functions with finite (p, m)-energy. These quasimetric spaces will be viewed both in $${\mathbb {C}}^n$$ C n and in compact Kähler manifolds, and their convergence will be used to improve known stability results for the complex Hessian equations.

show abstract

“…Moreover, the financial-nonfinancial future markets predictions are very helpful for those who are willing for financing in the market and for hedgers to hedge their financial assets [5,6]. The machine learning algorithms (MLAs) have capability to analyze the linear-nonlinear data [7].…”

Section: Introductionmentioning

confidence: 99%

Evaluation Optimal Prediction Performance of MLMs on High-volatile Financial Market Data

Yao¹,

Naveed²,

Answer³

et al. 2022

IJACSA

View full text Add to dashboard Cite

The present study evaluates the prediction performance of the multi-machine learning models (MLMs) on high-volatile financial markets data sets since 2007 to 2020. The linear and nonlinear empirical data sets are comprised on stock price returns of Karachi stock exchange (KSE) 100-Index of Pakistan and currencies exchange rates of Pakistani Rupees (PKR) against five major currencies (USD, Euro, GBP, CHF & JPY). In the present study, the support vector regression (SVR), random forest (RF), and machine learning-linear regression model (ML-LRM) are under-evaluated for comparative prediction performance. Moreover, the findings demonstrated that the SVR comparatively gives optimal prediction performance on group1. Similarly, the RF relatively gives the best prediction performance on group2. The findings of study concludes that the algorithm of RF is most appropriate for nonlinear approximation/evaluation and the algorithm of SVR is most useful for high-frequency time-series data estimation. The present study is contributed by exploring comparative enthusiastic/optimistic machine learning model on multi-nature data sets. This empirical study would be helpful for finance and machine-learning pupils, data analysts and researchers, especially for those who are deploying machine-learning approaches for financial analysis.

show abstract

Dreaming machine learning: Lipschitz extensions for reinforcement learning on financial markets

Cited by 24 publications

References 59 publications

Financial Abnormal Data Detection System Based on Reinforcement Learning

Financial Abnormal Data Detection System Based on Reinforcement Learning

On a Family of Quasimetric Spaces in Generalized Potential Theory

Evaluation Optimal Prediction Performance of MLMs on High-volatile Financial Market Data

Contact Info

Product

Resources

About