scholarly journals Application of multilayer perceptron to deep reinforcement learning for stock market trading and analysis

2021 ◽  
Vol 24 (3) ◽  
pp. 1759
Author(s):  
Hima Keerthi Sagiraju ◽  
Shashi Mogalla
Keyword(s):  
Stock Market ◽  
Multilayer Perceptron ◽  
Predictive Performance ◽  
Q Learning ◽  
Policy Gradient ◽  
The Individual ◽  
Policy Optimization ◽  
Stock Market Trading ◽  
Parameter Values ◽  
Sortino Ratio

Trading strategies to maximize profits by tracking and responding to dynamic stock market variations is a complex task. This paper proposes to use a multilayer perceptron method (a part of artificial neural networks (ANNs)), that can be used to deploy deep reinforcement strategies to learn the process of predicting and analyzing the stock market products with the aim to maximize profit making. We trained a deep reinforcement agent using the four algorithms: proximal policy optimization (PPO), deep Q-learning (DQN), deep deterministic policy gradient (DDPG) method, and advantage actor critic (A2C). The proposed system, comprising these algorithms, is tested using real time stock data of two products: Dow Jones (DJIA-index), and Qualcomm (shares). The performance of the agent linked to the individual algorithms was evaluated, compared and analyzed using Sharpe ratio, Sortino ratio, Skew and Kurtosis, thus leading to the most effective algorithm being chosen. Based on the parameter values, the algorithm that maximizes profit making for the respective financial product was determined. We also extended the same approach to study and ascertain the predictive performance of the algorithms on trading under highly volatile scenario, such as the pandemic coronavirus disease 2019 (COVID-19).

scholarly journals Artificial Intelligence Applied to Stock Market Trading: A Review

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 30898-30917 ◽  
Author(s):  
Fernando G. D. C. Ferreira ◽  
Amir H. Gandomi ◽  
Rodrigo T. N. Cardoso
Keyword(s):  
Artificial Intelligence ◽  
Stock Market ◽  
Stock Market Trading

PQROM: To optimize software defined network QoS-aware routing with proximal policy optimization

2021 ◽  
pp. 1-10
Author(s):  
Wei Zhou ◽  
Xing Jiang ◽  
Bingli Guo (Member, IEEE) ◽  
Lingyu Meng
Keyword(s):  
Software Defined Network ◽  
Training Time ◽  
Good Convergence ◽  
Reward Function ◽  
Routing Optimization ◽  
Policy Gradient ◽  
Discrete Action ◽  
Policy Optimization ◽  
Optimization Mechanism ◽  
Network Pattern

Currently, Quality-of-Service (QoS)-aware routing is one of the crucial challenges in Software Defined Network (SDN). The QoS performances, e.g. latency, packet loss ratio and throughput, must be optimized to improve the performance of network. Traditional static routing algorithms based on Open Shortest Path First (OSPF) could not adapt to traffic fluctuation, which may cause severe network congestion and service degradation. Central intelligence of SDN controller and recent breakthroughs of Deep Reinforcement Learning (DRL) pose a promising solution to tackle this challenge. Thus, we propose an on-policy DRL mechanism, namely the PPO-based (Proximal Policy Optimization) QoS-aware Routing Optimization Mechanism (PQROM), to achieve a general and re-customizable routing optimization. PQROM can dynamically update the routing calculation by adjusting the reward function according to different optimization objectives, and it is independent of any specific network pattern. Additionally, as a black-box one-step optimization, PQROM is qualified for both continuous and discrete action space with high-dimensional input and output. The OMNeT ++ simulation experiment results show that PQROM not only has good convergence, but also has better stability compared with OSPF, less training time and simpler hyper-parameters adjustment than Deep Deterministic Policy Gradient (DDPG) and less hardware consumption than Asynchronous Advantage Actor-Critic (A3C).

scholarly journals A modular approach to integrating multiple data sources into real-time clinical prediction for pediatric diarrhea

2020 ◽  
Author(s):  
Ben J. Brintz ◽  
Benjamin Haaland ◽  
Joel Howard ◽  
Dennis L. Chao ◽  
Joshua L. Proctor ◽  
...  
Keyword(s):  
Real Time ◽  
Prediction Models ◽  
Predictive Performance ◽  
Data Availability ◽  
Clinical Prediction ◽  
Multiple Sources ◽  
Statistical Framework ◽  
Multiple Data ◽  
Post Test ◽  
The Individual

AbstractTraditional clinical prediction models focus on parameters of the individual patient. For infectious diseases, sources external to the patient, including characteristics of prior patients and seasonal factors, may improve predictive performance. We describe the development of a predictive model that integrates multiple sources of data in a principled statistical framework using a post-test odds formulation. Our method enables electronic real-time updating and flexibility, such that components can be included or excluded according to data availability. We apply this method to the prediction of etiology of pediatric diarrhea, where “pre-test” epidemiologic data may be highly informative. Diarrhea has a high burden in low-resource settings, and antibiotics are often over-prescribed. We demonstrate that our integrative method outperforms traditional prediction in accurately identifying cases with a viral etiology, and show that its clinical application, especially when used with an additional diagnostic test, could result in a 61% reduction in inappropriately prescribed antibiotics.

Single step estimation of ARMA roots for non-fundamental nonstationary fractional models

2022 ◽  
Author(s):  
Ignacio N Lobato ◽  
Carlos Velasco
Keyword(s):  
Stock Market ◽  
Strong Evidence ◽  
Long Memory ◽  
Trading Volume ◽  
Moving Average ◽  
Single Step ◽  
Arma Process ◽  
Dow Jones Industrial Average ◽  
Fractional Models ◽  
Stock Market Trading

Abstract We propose a single step estimator for the autoregressive and moving-average roots (without imposing causality or invertibility restrictions) of a nonstationary Fractional ARMA process. These estimators employ an efficient tapering procedure, which allows for a long memory component in the process, but avoid estimating the nonstationarity component, which can be stochastic and/or deterministic. After selecting automatically the order of the model, we robustly estimate the AR and MA roots for trading volume for the thirty stocks in the Dow Jones Industrial Average Index in the last decade. Two empirical results are found. First, there is strong evidence that stock market trading volume exhibits non-fundamentalness. Second, non-causality is more common than non-invertibility.

Text and Discourse Linguistic Creativity of Children's English-Language Adventure Fiction

2021 ◽  
pp. 5-15
Author(s):  
Maria I. Kiose ◽  
◽  
Keyword(s):  
Vector Space ◽  
English Language ◽  
Total Sample ◽  
Word Formation ◽  
Statistics Analysis ◽  
Individual Parameter ◽  
Creativity Assessment ◽  
Adventure Fiction ◽  
The Individual ◽  
Parameter Values

The article explores the specificity of linguistic creativity in the discourse of children's English-language adventure fiction of the 1950s. The aim of the research is to develop the parametrization and vector-space method of discourse and text linguistic creativity assessment to evaluate the linguistic creativity potential of individual texts displaying similar discourse features. To serve as the research data three discourse fragments were selected, which represent three basic narrative types, Orientation, Complicating Actions, Evaluation and Resolution. To achieve the aim, the author applies the procedure of parametrization analysis followed by general and analytic statistics analysis and vector-space modelling. With the system of 52 parameters featuring linguistic creativity in phonology, word-formation, morphology, lexicology and phraseology, syntax, and graphics, the author manually annotates and processes the discourse fragments of similar size exemplifying three narrative types of adventure fiction literature, with the total sample size of 55,000 characters. General statistics analysis allowed revealing the absolute and relative parameter values in three discourse fragments and defining the relative parametric activity of single parameters and parameter levels. Analysis of variance helped define the correlation indices of parameter paired combinations, which resulted in detecting significant binary parameter groups . Individual parameter values and their binary groups served to construe the vector-space models of discourse and text linguistic creativity for the discourse narrative types under consideration. Thus, the author obtained an efficient instrument for discourse linguistic creativity evaluation and, furthermore, for assessing the potential of each individual text in terms of displaying stronger or weaker correlation with the vector coordinates of the discourse linguistic creativity vector-space model. With the frequency and variance analysis, the author disclosed two types of discourse linguistic creativity performance techniques, that is the individual parameter activation and the parameter synchronization. Both must be considered when the decision on linguistic creativity assessment in a concrete text is made. The resulting model shows that the parameter values of linguistic creativity in individual texts can manifest themselves in appearing both higher and lower than the reference parameter values of discourse creativity, which can contribute to disclosing new directions in creativity processing and understanding.

scholarly journals Machine Learning Readmission Risk Modeling: A Pediatric Case Study

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Patricio Wolff ◽  
Manuel Graña ◽  
Sebastián A. Ríos ◽  
Maria Begoña Yarza
Keyword(s):  
Machine Learning ◽  
Multilayer Perceptron ◽  
Naive Bayes ◽  
Class Imbalance ◽  
Predictive Performance ◽  
Naïve Bayes ◽  
Distribution Model ◽  
Training Dataset ◽  
Support Vector ◽  
Pediatric Hospital

Background. Hospital readmission prediction in pediatric hospitals has received little attention. Studies have focused on the readmission frequency analysis stratified by disease and demographic/geographic characteristics but there are no predictive modeling approaches, which may be useful to identify preventable readmissions that constitute a major portion of the cost attributed to readmissions.Objective. To assess the all-cause readmission predictive performance achieved by machine learning techniques in the emergency department of a pediatric hospital in Santiago, Chile.Materials. An all-cause admissions dataset has been collected along six consecutive years in a pediatric hospital in Santiago, Chile. The variables collected are the same used for the determination of the child’s treatment administrative cost.Methods. Retrospective predictive analysis of 30-day readmission was formulated as a binary classification problem. We report classification results achieved with various model building approaches after data curation and preprocessing for correction of class imbalance. We compute repeated cross-validation (RCV) with decreasing number of folders to assess performance and sensitivity to effect of imbalance in the test set and training set size.Results. Increase in recall due to SMOTE class imbalance correction is large and statistically significant. The Naive Bayes (NB) approach achieves the best AUC (0.65); however the shallow multilayer perceptron has the best PPV and f-score (5.6 and 10.2, resp.). The NB and support vector machines (SVM) give comparable results if we consider AUC, PPV, and f-score ranking for all RCV experiments. High recall of deep multilayer perceptron is due to high false positive ratio. There is no detectable effect of the number of folds in the RCV on the predictive performance of the algorithms.Conclusions. We recommend the use of Naive Bayes (NB) with Gaussian distribution model as the most robust modeling approach for pediatric readmission prediction, achieving the best results across all training dataset sizes. The results show that the approach could be applied to detect preventable readmissions.

scholarly journals Bootstrap Estimation of Expected Risk and Return of Strategy Equity Indices

2020 ◽  
Vol 28 (2) ◽  
pp. 111-120
Author(s):  
Veronika Novotná ◽  
Stanislav Škapa
Keyword(s):  
Momentum Strategy ◽  
Bootstrap Estimation ◽  
Ex Post ◽  
Yield Risk ◽  
Suitable Combination ◽  
The Individual ◽  
Equity Index ◽  
Equity Indices ◽  
Sortino Ratio

The aim of this article is to present the results of research associated with the ex-post estimation of expected risk, return and other characteristics of strategy equity indices and capital-weighted equity indices partially and to determine credible methods for a transparent comparison. The data sources are the MSCI and STOXX equity index providers. Suitable statistical methods and a computation-intensive method for estimating selected characteristics have been used and compared to one another.For the measurement of excess return per unit of risk a modified Sortino ratio was used, which takes into account only the downside size and frequency of returns, measuring the return to negative volatility trade-off. Based on our results, it is apparent that some strategic equity indices outperform capital-weighted equity indices in a long-term investment perspective (1997-2018).A suitable combination of strategic equity indices, namely the mix of dividend strategy and momentum strategy may lead to the highest yield / risk ratio expressed by the Sortino ratio. The outperformance path of a mix of dividends and momentum strategy indices is much more stable than either the performance of the individual strategy equity indices or capital-weighted equity indices alone.

Sign in / Sign up

Export Citation Format

Share Document