Subjects -> COMPUTER SCIENCE (Total: 2313 journals)     - ANIMATION AND SIMULATION (33 journals)    - ARTIFICIAL INTELLIGENCE (133 journals)    - AUTOMATION AND ROBOTICS (116 journals)    - CLOUD COMPUTING AND NETWORKS (75 journals)    - COMPUTER ARCHITECTURE (11 journals)    - COMPUTER ENGINEERING (12 journals)    - COMPUTER GAMES (23 journals)    - COMPUTER PROGRAMMING (25 journals)    - COMPUTER SCIENCE (1305 journals)    - COMPUTER SECURITY (59 journals)    - DATA BASE MANAGEMENT (21 journals)    - DATA MINING (50 journals)    - E-BUSINESS (21 journals)    - E-LEARNING (30 journals)    - ELECTRONIC DATA PROCESSING (23 journals)    - IMAGE AND VIDEO PROCESSING (42 journals)    - INFORMATION SYSTEMS (109 journals)    - INTERNET (111 journals)    - SOCIAL WEB (61 journals)    - SOFTWARE (43 journals)    - THEORY OF COMPUTING (10 journals) COMPUTER SCIENCE (1305 journals)            First | 1 2 3 4 5 6 7 | Last
 Showing 201 - 400 of 872 Journals sorted alphabetically Computational Ecology and Software       (Followers: 9) Computational Economics       (Followers: 12) Computational Geosciences       (Followers: 17) Computational Linguistics       (Followers: 23) Computational Management Science Computational Mathematics and Modeling       (Followers: 8) Computational Mechanics       (Followers: 11) Computational Methods and Function Theory Computational Molecular Bioscience       (Followers: 1) Computational Optimization and Applications       (Followers: 9) Computational Particle Mechanics       (Followers: 1) Computational Science and Techniques Computational Statistics       (Followers: 15) Computational Statistics & Data Analysis       (Followers: 35) Computational Toxicology Computer       (Followers: 141) Computer Aided Surgery       (Followers: 5) Computer Applications in Engineering Education       (Followers: 6) Computer Communications       (Followers: 19) Computer Engineering and Applications Journal       (Followers: 8) Computer Journal       (Followers: 7) Computer Methods in Applied Mechanics and Engineering       (Followers: 26) Computer Methods in Biomechanics and Biomedical Engineering       (Followers: 10) Computer Methods in Biomechanics and Biomedical Engineering : Imaging & Visualization Computer Music Journal       (Followers: 18) Computer Physics Communications       (Followers: 9) Computer Science - Research and Development       (Followers: 7) Computer Science and Engineering       (Followers: 15) Computer Science and Information Technology       (Followers: 12) Computer Science Education       (Followers: 16) Computer Science Journal       (Followers: 20) Computer Science Review       (Followers: 12) Computer Standards & Interfaces       (Followers: 3) Computer Supported Cooperative Work (CSCW)       (Followers: 8) Computer-aided Civil and Infrastructure Engineering       (Followers: 9) Computer-Aided Design and Applications       (Followers: 6) Computers       (Followers: 2) Computers & Chemical Engineering       (Followers: 12) Computers & Education       (Followers: 92) Computers & Electrical Engineering       (Followers: 8) Computers & Geosciences       (Followers: 30) Computers & Mathematics with Applications       (Followers: 9) Computers & Structures       (Followers: 44) Computers & Education Open       (Followers: 3) Computers & Industrial Engineering       (Followers: 6) Computers and Composition       (Followers: 11) Computers and Education: Artificial Intelligence       (Followers: 5) Computers and Electronics in Agriculture       (Followers: 7) Computers and Geotechnics       (Followers: 13) Computers in Biology and Medicine       (Followers: 10) Computers in Entertainment Computers in Human Behavior Reports Computers in Industry       (Followers: 7) Computers in the Schools       (Followers: 8) Computers, Environment and Urban Systems       (Followers: 11) Computerworld Magazine       (Followers: 2) Computing       (Followers: 2) Computing and Software for Big Science       (Followers: 1) Computing and Visualization in Science       (Followers: 6) Computing in Science & Engineering       (Followers: 31) Computing Reviews       (Followers: 1) Concurrency and Computation: Practice & Experience Connection Science Control Engineering Practice       (Followers: 46) Cryptologia       (Followers: 3) CSI Transactions on ICT       (Followers: 2) Cuadernos de Documentación Multimedia Current Science       (Followers: 117) Cyber-Physical Systems Cyberspace : Jurnal Pendidikan Teknologi Informasi DAIMI Report Series Data       (Followers: 4) Data & Policy       (Followers: 3) Data Science       (Followers: 6) Data Science and Engineering       (Followers: 6) Data Technologies and Applications       (Followers: 217) Data-Centric Engineering       (Followers: 1) Datenbank-Spektrum       (Followers: 1) Datenschutz und Datensicherheit - DuD Decision Analytics       (Followers: 3) Decision Support Systems       (Followers: 13) Design Journal : An International Journal for All Aspects of Design       (Followers: 33) Digital Biomarkers       (Followers: 1) Digital Chemical Engineering Digital Chinese Medicine Digital Creativity       (Followers: 11) Digital Experiences in Mathematics Education       (Followers: 3) Digital Finance : Smart Data Analytics, Investment Innovation, and Financial Technology       (Followers: 3) Digital Geography and Society Digital Government : Research and Practice       (Followers: 1) Digital Health       (Followers: 10) Digital Journalism       (Followers: 8) Digital Medicine       (Followers: 3) Digital Platform: Information Technologies in Sociocultural Sphere       (Followers: 1) Digital Policy, Regulation and Governance       (Followers: 2) Digital War       (Followers: 2) Digitale Welt : Das Wirtschaftsmagazin zur Digitalisierung Digitális Bölcsészet / Digital Humanities       (Followers: 2) Disaster Prevention and Management       (Followers: 30) Discours       (Followers: 1) Discourse & Communication       (Followers: 26) Discover Internet of Things       (Followers: 2) Discrete and Continuous Models and Applied Computational Science Discrete Event Dynamic Systems       (Followers: 3) Discrete Mathematics & Theoretical Computer Science       (Followers: 1) Discrete Optimization       (Followers: 7) Displays Distributed and Parallel Databases       (Followers: 2) e-learning and education (eleed)       (Followers: 40) Ecological Indicators       (Followers: 22) Ecological Informatics       (Followers: 3) Ecological Management & Restoration       (Followers: 15) Ecosystems       (Followers: 33) Edu Komputika Journal       (Followers: 1) Education and Information Technologies       (Followers: 53) Educational Philosophy and Theory       (Followers: 10) Educational Psychology in Practice: theory, research and practice in educational psychology       (Followers: 13) Educational Research and Evaluation: An International Journal on Theory and Practice       (Followers: 7) Educational Theory       (Followers: 9) Egyptian Informatics Journal       (Followers: 5) Electronic Commerce Research and Applications       (Followers: 5) Electronic Design       (Followers: 125) Electronic Letters on Computer Vision and Image Analysis       (Followers: 10) Elektron Empirical Software Engineering       (Followers: 8) Energy for Sustainable Development       (Followers: 13) Engineering & Technology       (Followers: 23) Engineering Applications of Computational Fluid Mechanics       (Followers: 23) Engineering Computations       (Followers: 3) Engineering Economist, The       (Followers: 4) Engineering Optimization       (Followers: 19) Engineering With Computers       (Followers: 5) Enterprise Information Systems       (Followers: 2) Entertainment Computing       (Followers: 2) Environmental and Ecological Statistics       (Followers: 7) Environmental Communication: A Journal of Nature and Culture       (Followers: 16) EPJ Data Science       (Followers: 10) ESAIM: Control Optimisation and Calculus of Variations       (Followers: 2) Ethics and Information Technology       (Followers: 64) eTransportation       (Followers: 1) EURO Journal on Computational Optimization       (Followers: 5) EuroCALL Review European Food Research and Technology       (Followers: 8) European Journal of Combinatorics       (Followers: 3) European Journal of Computational Mechanics       (Followers: 1) European Journal of Information Systems       (Followers: 86) European Journal of Law and Technology       (Followers: 19) European Journal of Political Theory       (Followers: 28) Evolutionary Computation       (Followers: 11) Fibreculture Journal       (Followers: 9) Finite Fields and Their Applications       (Followers: 5) Fixed Point Theory and Applications Focus on Catalysts Focus on Pigments       (Followers: 3) Focus on Powder Coatings       (Followers: 5) Forensic Science International: Digital Investigation       (Followers: 319) Formal Aspects of Computing       (Followers: 3) Formal Methods in System Design       (Followers: 6) Forschung       (Followers: 1) Foundations and Trends® in Communications and Information Theory       (Followers: 6) Foundations and Trends® in Databases       (Followers: 2) Foundations and Trends® in Human-Computer Interaction       (Followers: 5) Foundations and Trends® in Information Retrieval       (Followers: 30) Foundations and Trends® in Networking       (Followers: 1) Foundations and Trends® in Signal Processing       (Followers: 7) Foundations and Trends® in Theoretical Computer Science       (Followers: 1) Foundations of Computational Mathematics Foundations of Computing and Decision Sciences Frontiers in Computational Neuroscience       (Followers: 23) Frontiers in Computer Science       (Followers: 1) Frontiers in Digital Health       (Followers: 4) Frontiers in Digital Humanities       (Followers: 7) Frontiers in ICT Frontiers in Neuromorphic Engineering       (Followers: 2) Frontiers in Research Metrics and Analytics       (Followers: 4) Frontiers of Computer Science in China       (Followers: 2) Frontiers of Environmental Science & Engineering       (Followers: 3) Frontiers of Information Technology & Electronic Engineering Fuel Cells Bulletin       (Followers: 9) Functional Analysis and Its Applications       (Followers: 3) Future Computing and Informatics Journal Future Generation Computer Systems       (Followers: 2) Geo-spatial Information Science       (Followers: 7) Geoforum Perspektiv       (Followers: 1) GeoInformatica       (Followers: 7) Geoinformatics FCE CTU       (Followers: 8) GetMobile : Mobile Computing and Communications       (Followers: 1) Government Information Quarterly       (Followers: 28) Granular Computing Graphics and Visual Computing Grey Room       (Followers: 16) Group Dynamics : Theory, Research, and Practice       (Followers: 15) Groups, Complexity, Cryptology       (Followers: 2) HardwareX Harvard Data Science Review       (Followers: 3) Health Services Management Research       (Followers: 16) Healthcare Technology Letters High Frequency High-Confidence Computing       (Followers: 1) Home Cultures       (Followers: 7)
Similar Journals
 Computational EconomicsJournal Prestige (SJR): 0.433 Citation Impact (citeScore): 1Number of Followers: 12      Hybrid journal (It can contain Open Access articles) ISSN (Print) 1572-9974 - ISSN (Online) 0927-7099 Published by Springer-Verlag  [2469 journals]
• Portfolio Optimization Via Online Gradient Descent and Risk Control

Abstract: Abstract Since Markowitz’s initial contribution in 1952, portfolio selection has undoubtedly been one of the most challenging topics in finance. The development of online optimization techniques indicates that dynamic learning algorithms are an effective approach to portfolio construction, although they do not evaluate the risk associated with each investment decision. In this work, the performance of the well-known Online Gradient Descent (OGD) algorithm is evaluated in comparison with a proposed approach that incorporates portfolio risk using $$\beta$$ control of portfolio assets modeled with the CAPM strategy and considering a time-varying $$\beta$$ that follows a random walk. Thus, the traditional OGD algorithm and the OGD with $$\beta$$ constraints are compared with the Uniform Constant Rebalanced Portfolio (UCRP) and two specific indexes for the Brazilian market, consisting of small caps and the assets belonging to the Bovespa index. The experiments have shown that $$\beta$$ control, combined with an appropriate definition of the $$\beta$$ interval by the investor, is an efficient strategy, regardless of market periods with gains or losses. Moreover, time-varying $$\beta$$ has been shown to be an efficient measure to force the desired correlation with the market and also to reduce the volatility of the portfolio, especially during hazardous bear markets.
PubDate: 2022-06-30

• Quasi-Monte Carlo-Based Conditional Malliavin Method for Continuous-Time
Asian Option Greeks

Abstract: Abstract Although many methods for computing the Greeks of discrete-time Asian options are proposed, few methods to calculate the Greeks of continuous-time Asian options are known. In this paper, we develop an integration by parts formula in the multi-dimensional Malliavin calculus, and apply it to obtain the Greeks formulae for continuous-time Asian options in the multi-asset situation. We combine the Malliavin method with the quasi-Monte Carlo method to calculate the Greeks in simulation. We discuss the asymptotic convergence of simulation estimates for the continuous-time Asian option Greeks obtained by Malliavin derivatives. We propose to use the conditional quasi-Monte Carlo method to smooth Malliavin Greeks, and show that the calculation of conditional expectations analytically is viable for many types of Asian options. We prove that the new estimates for Greeks have good smoothness. For binary Asian options, Asian call options and up-and-out Asian call options, for instance, our estimates are infinitely times differentiable. We take the gradient principal component analysis method as a dimension reduction technique in simulation. Numerical experiments demonstrate the large efficiency improvement of the proposed method, especially for Asian options with discontinuous payoff functions.
PubDate: 2022-06-21

• Optimal Limit Order Book Trading Strategies with Stochastic Volatility in
the Underlying Asset

Abstract: Abstract In quantitative finance, there have been numerous new aspects and developments related with the stochastic control and optimization problems which handle the controlled variables of performing the behavior of a dynamical system to achieve certain objectives. In this paper, we address the optimal trading strategies via price impact models using Heston stochastic volatility framework including jump processes either in price or in volatility of the price dynamics with the aim of maximizing expected return of the trader by controlling the inventories. Two types of utility functions are considered: quadratic and exponential. In both cases, the remaining inventories of the market maker are charged with a liquidation cost. In order to achieve the optimal quotes, we control the inventory risk and follow the influence of each parameter in the model to the best bid and ask prices. We show that the risk metrics including profit and loss distribution (PnL), standard deviation and Sharpe ratio play important roles for the trader to make decisions on the strategies. We apply finite differences and linear interpolation as well as extrapolation techniques to obtain a solution of the nonlinear Hamilton-Jacobi-Bellman (HJB) equation. Moreover, we consider different cases on the modeling to carry out the numerical simulations.
PubDate: 2022-06-17

• Forecasting Forex Trend Indicators with Fuzzy Rough Sets

Abstract: Abstract We propose a machine-learning approach for Forex prices that forecasts trends in terms of whether or not the closing price will change for more than a threshold and whether that change is an increase or a decrease. Instead of using the prices as such, we carry out the forecast solely in terms of indicators that are popular among small-scale traders; our goal is to determine whether these convey sufficient information for a precise forecast for different change thresholds and horizons. Fuzzy rough sets are used to represent and select among multiple economic indicators and to construct a classifier to forecast price changes. High-quality forecasts are feasible for short horizons and for small thresholds of change for all fifteen currency pairs studied in the experiments.
PubDate: 2022-06-15

• A Comprehensive Study of Market Prediction from Efficient Market
Hypothesis up to Late Intelligent Market Prediction Approaches

Abstract: Abstract This paper has scrutinized the process of testing market efficiency, data generation process and the feasibility of market prediction with a detailed, coherent and statistical approach. Furthermore, attempts are made to extract knowledge from S&P 500 market data with an emphasize on feature engineering. As such, different data representations are provided through different procedures, and their performance in knowledge extraction is discussed. Amongst the neural networks, Long Short-Term Memory has not been adequately experimented. LSTM, because of its intrinsic, considers the long-term and short-term memory in its computations. Thus, in this paper LSTM is further examined in return prediction and different preprocessing methods are tested to improve its accuracy. This study is conducted on market data during September-2000 to February-2021. In order to extend the amount of knowledge extracted from financial time series, and to select the best input features, the advantage of Principal Component Analyze, Random Forest, Wavelet and the LSTM’s own deep feature extraction procedure are taken, and 4 models are compiled. Subsequently, to validate the performance of the models, MAE, MSE, MAPE, CSP and CDCP are calculated. Results from Diebold Mariano test implied that although LSTM neural network has gained a lot of attention recently, it does not significantly perform better than the benchmark method in S&P 500 index return prediction. Yet, results from Wilcoxon signed rank test showed the significance of improvement in the predictions performed by the combination of Principal component analysis and LSTM.
PubDate: 2022-06-14

• Exploring Uncertainty, Sensitivity and Robust Solutions in Mathematical
Programming Through Bayesian Analysis

Abstract: Abstract The paper examines the effect of uncertainty on the solution of mathematical programming problems, using Bayesian techniques. We show that the statistical inference of the unknown parameter lies in the solution vector itself. Uncertainty in the data is modeled using sampling models induced by constraints. In this context, the objective is used as prior, and the posterior is efficiently applied via Monte Carlo methods. The proposed techniques provide a new benchmark for robust solutions that are designed without solving mathematical programming problems. We illustrate the benefits of a problem with known solutions and their properties, while discussing the empirical aspects in a real-world portfolio selection problem.
PubDate: 2022-06-10

• Classifying the Variety of Customers’ Online Engagement for Churn
Prediction with a Mixed-Penalty Logistic Regression

Abstract: Abstract Using big data to analyze consumer behavior can provide effective decision-making tools for preventing customer attrition (churn) in customer relationship management (CRM). Focusing on a CRM dataset with several different categories of factors that impact customer heterogeneity (i.e., usage of self-care service channels, service duration, and responsiveness to marketing actions), this research provides new predictive analytics of customer churn rate based on a machine learning method that enhances the classification of logistic regression by adding a mixed penalty term. The proposed penalized logistic regression prevents overfitting when dealing with big data and minimizes the loss function when balancing the cost from the median (absolute value) and mean (squared value) regularization. We show the analytical properties of the proposed method and its computational advantage in this research. In addition, we investigate the performance of the proposed method with a CRM dataset (that has a large number of features) under different settings by efficiently eliminating the disturbance of (1) least important features and (2) sensitivity from the minority (churn) class. Our empirical results confirm the expected performance of the proposed method in full compliance with the common classification criteria (i.e., accuracy, precision, and recall) for evaluating machine learning methods.
PubDate: 2022-06-10

• A Synthetic Data-Plus-Features Driven Approach for Portfolio Optimization

Abstract: Abstract Features, or contextual information, are additional data than can help predicting asset returns in financial problems. We propose a mean-risk portfolio selection problem that uses contextual information to maximize expected returns at each time period, weighing past observations via kernels based on the current state of the world. We consider yearly intervals for investment opportunities, and a set of indices that cover the most relevant investment classes. For those intervals, data scarcity is a problem that is often dealt with by making distribution assumptions. We take a different path and use distribution-free simulation techniques to populate our database. In our experiments we use the Conditional Value-at-Risk as our risk measure, and we work with data from 2007 until 2021 to evaluate our methodology. Our results show that, by incorporating features, the out-of-sample performance of our strategy outperforms the equally-weighted portfolio. We also generate diversified positions, and efficient frontiers that exhibit coherent risk-return patterns.
PubDate: 2022-06-07

• Predict Stock Prices Using Supervised Learning Algorithms and Particle
Swarm Optimization Algorithm

Abstract: Abstract Forecasting the stock market has always been one of the challenges for stock market participants to make more profit. Among the problems of stock price forecasting, we can mention its dynamic nature, complexity and its dependence on factors such as the governing system of countries, emotions, economic conditions, inflation, and so on. In recent years, many studies have been conducted to predict the capital stock market using traditional techniques, machine learning algorithms and deep learning. The lower our forecast stock error, the More we can reduce investment risk and increase profitability. In this paper, we present a machine learning (ML) approach called support vector machine (SVM) that can be taught using existing data. SVM extracts knowledge between data and ultimately uses this knowledge to predict new stock data. We have also aimed to select the best SVM method parameters using the particle swarm optimization (PSO) algorithm to prevent over-fitting and improve forecast accuracy. Finally, we compare our proposed method (SVM-PSO) with several other methods, including support vector machine, artificial neural network (ANN) and LSTM. The results show that the proposed algorithm works better than other methods and in all cases, its forecast accuracy is above 90%.
PubDate: 2022-06-05

• A Deep Learning Based Numerical PDE Method for Option Pricing

Abstract: Abstract Proper pricing of options in the financial derivative market is crucial. For many options, it is often impossible to obtain analytical solutions to the Black–Scholes (BS) equation. Hence an accurate and fast numerical method is very beneficial for option pricing. In this paper, we use the Physics-Informed Neural Networks (PINNs) method recently developed by Raissi et al. (J Comput Phys 378:686–707, 2019) to solve the BS equation. Many experiments have been carried out for solving various option pricing models. Compared with traditional numerical methods, the PINNs based method is simple in implementation, but with comparable accuracy and computational speed, which illustrates a promising potential of deep neural networks for solving more complicated BS equations.
PubDate: 2022-06-02

• House Prices as a Result of Trading Activities: A Patient Trader Model

Abstract: Abstract We present a new modeling approach for house price movements as a consequence of the trading behavior of market agents. In our modeling approach, all agents are assumed to assign a personal threshold value to a (standardized) house and update the threshold value permanently by a continuous-time filtering procedure based on observing the quoted house prices and the resulting price movements. The traders then trade according to a threshold price strategy (try to sell if the personal threshold value is lower, try to buy if the personal threshold value is higher than the actually quoted house price). Our modeling approach and its resulting characteristics are illustrated via numerical examples that highlight certain realistic constellations between various traders.
PubDate: 2022-06-01

• DeepValue: A Comparable Framework for Value-Based Strategy by Machine
Learning

Abstract: Abstract Value relevant analysis is one of the key stock trading strategies of stock investment which is based on financial statement that represents the intrinsic investing value of firms. Human analysts have dominated the value interpretation of companies so far, in spite of the numerous efforts being made by machine learning researchers nowadays. The complexity of hundreds of accounting terms in financial statements and the latent interaction among industrial contextual factors are hard to be integrated into machine learning approaches. The analysis of profitability and potential for specific companies are often unique and not applicable to the others. In this paper, we constitute a unified learning framework, named as DeepValue, for knowledge transfer from and value extraction of collective financial status for value-based investment strategy. We validate four kinds of feature set from 11 years of financial statements of 90 semiconductor companies in TWSE. It incorporates deep Learning surrogate function for feature mapping, Multitask Learning (MTL) for knowledge transfer and feature sharing, and Long Short-Term Memory (LSTM) for value extraction. This value is then used to assess the degree of value-price gaps for stock selection. Experiment results demonstrate that the proposed framework is able to quantify the potential of stocks. The derived recommendation lists significantly outperform market and EPS-based selection.
PubDate: 2022-06-01

• Menu Optimization for Multi-Profile Customer Systems on Large Scale Data

Abstract: Abstract Everyday, a majority of the people, most probably several times, use the banking applications through online applications or physical ATM (Automated Teller Machine) devices for managing their financial transactions. However, most financial institutions provide static user interfaces regardless of the needs for different customers. Saving even a few seconds for each transaction through more personalized interface design might not only result in higher efficiency, but also result in customer satisfaction and increased market share among the competitors. In ATM Graphical User Interface (GUI) design, transaction completion time is, arguably, one of the most important metrics to quantify customer satisfaction. Optimizing GUI menu structures has been pursued and many heuristic techniques for this purpose are present. However, menu optimization by employing an exact mathematical optimization framework has never been performed in the literature. We cast the ATM menu optimization problem as a Mixed Integer Programming (MIP) framework. All the parameters of the MIP framework are derived from a comprehensive actual ATM menu usage database. We also proposed two heuristic approaches to reduce the computational complexity. Our solution can be accustomed with ergonomic factors and can easily be tailored for optimization of various menu design problems. Performance evaluations of our solutions by using actual ATM data reveal the superior performance of our optimization solution.
PubDate: 2022-06-01

• Optimized Machine Learning Algorithms for Investigating the Relationship
Between Economic Development and Human Capital

Abstract: Abstract In Economic Development, human capital was previously seen as production factors but gradually evolved into endogenous growth theories. Most of the previous studies have examined the relationships between economic development and human capital via econometric models. Since this relationship is usually nonlinear and machine learning (ML) models can resolve it better, this study investigates the relationships by employing ML methods to provide a new perspective. For this purpose, the optimized ML methods, namely Bayesian Tuned Support Vector Machine and Bayesian Tuned Gaussian Process Regression (BT-GPR), were performed to develop the prediction model for economic development. The hyperparameters have been optimized with the Bayes method by using different kernel functions to increase SVM and GPR methods' predictive performance. The Multiple Linear Regression model has been employed to make a comparison as an econometric model. The performance of the models is evaluated using three statistical metrics, namely, the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The BT-GPR with the exponential kernel model has superior prediction ability with the highest accuracy (R2: 0.9727, RMSE: 0.4022, MAE: 0.3728 in the testing phase). The study shows that the BT-GPR model increases the accuracy of R2 6.4%, RMSE 10.7%, and MAE 1% compared with other developed models.
PubDate: 2022-06-01

• Towards Crafting Optimal Functional Link Artificial Neural Networks with
Rao Algorithms for Stock Closing Prices Prediction

Abstract: Abstract Quite a good number of population-based meta-heuristics based on mimicking natural phenomena are observed in the literature in resolving varieties of complex optimization problems. They are widely used in search of the optimal model parameters of artificial neural networks (ANNs). However, efficiencies of these are mostly dependent on fine tuning algorithm-specific parameters. Rao algorithms are metaphor-less meta-heuristics which do not need any algorithm-specific parameters. Functional link artificial neural network (FLANN) is a flat network and possesses the ability of mapping input–output nonlinear relationships by using amplification in input vector dimension. This article attempts to observe the efficacy of Rao algorithms on searching the most favorable parameters of FLANN, thus forming hybrid models termed as Rao algorithm-based FLANNs (RAFLANNs). The models are evaluated on forecasting five stock markets such as NASDAQ, BSE, DJIA, HSI, and NIKKEI. The RAFLANNs performances are compared with that of variations of FLANN (i.e., FLANN based on gradient descent, multi-verse optimizer, monarch butterfly optimization and genetic algorithm) and conventional models (i.e., MLP, SVM and ARIMA). The proposed models are found better in terms of prediction accuracy, computation time and statistical significance test.
PubDate: 2022-06-01

• The Effect of Including Irrelevant Alternatives in Discrete Choice Models
of Recreation Demand

Abstract: Abstract We measure bias and efficiency of parameter estimates in the conditional logit (CL) and independent availability logit (IAL) models. Our Monte Carlo experiments consider both no choice set formation where individuals choose from the full set of alternatives, and when choice sets are stochastically formed and individuals choose from a subset of all alternatives. We also compare the performance of the two models using empirical data on paddlefish angler preferences and catch-and-release regulations in Oklahoma. Both the CL and IAL work well when their own assumptions hold, but not under the alternative’s assumptions. The IAL approximates the attribute-based cutoff well in empirical data. While neither the IAL nor the CL is universally preferred, based on our findings, we recommend the IAL when the true consideration sets are unknown.
PubDate: 2022-06-01

• Is Deep-Learning and Natural Language Processing Transcending the
Financial Forecasting' Investigation Through Lens of News Analytic
Process

Abstract: Abstract This study tries to unravel the stock market prediction puzzle using the textual analytic with the help of natural language processing (NLP) techniques and Deep-learning recurrent model called long short term memory (LSTM). Instead of using count-based traditional sentiment index methods, the study uses its own sum and relevance based sentiment index mechanism. Hourly price data has been used in this research as daily data is too late and minutes data is too early for getting the exclusive effect of sentiments. Normally, hourly data is extremely costly and difficult to manage and analyze. Hourly data has been rarely used in similar kinds of researches. To built sentiment index, text analytic information has been parsed and analyzed, textual information that is relevant to selected stocks has been collected, aggregated, categorized, and refined with NLP and eventually converted scientifically into hourly sentiment index. News analytic sources include mainstream media, print media, social media, news feeds, blogs, investors’ advisory portals, experts’ opinions, brokers updates, web-based information, company’ internal news and public announcements regarding policies and reforms. The results of the study indicate that sentiments significantly influence the direction of stocks, on average after 3–4 h. Top ten companies from High-tech, financial, medical, automobile sectors are selected, and six LSTM models, three for using text-analytic and other without analytic are used. Every model includes 1, 3, and 6 h steps back. For all sectors, a 6-hour steps based model outperforms the other models due to LSTM specialty of keeping long term memory. Collective accuracy of textual analytic models is way higher relative to non-textual analytic models.
PubDate: 2022-06-01

• Need to Meet Investment Goals' Track Synthetic Indexes with the SDDP
Method

Abstract: Abstract This work presents a novel application of the Stochastic Dual Dynamic Problem (SDDP) to large-scale asset allocation. We construct a model that delivers allocation policies based on how the portfolio performs with respect to user-defined (synthetic) indexes, and implement it in a SDDP open-source package. Based on US economic cycles and ETF data, we generate Markovian regime-dependent returns to solve an instance of multiple assets and 28 time periods. Results show our solution outperforms its benchmark, in both profitability and tracking error.
PubDate: 2022-06-01

• The Geometry of the World of Currency Volatilities

Abstract: Abstract Using empirical data and the properties they reveal, we develop a factor that captures changes of both currency implied correlation and volatilities. For this purpose, we apply the Guldin–Pappus theorem in Euclidean space for rotating triangles to construct a specific factor, which we define as gravity radius. This approach allows the construction of a portfolio index aggregating all currency pairwise trades. Our factor, which is a weighted sum of all gravity radius factors in a portfolio, exhibits characteristics that are similar to the well-known turbulence metric defined in the literature and has moderate correlation to the CBOE VIX index. This factor therefore can serve as a risk indicator. We argue that the changes in volatilities impact the gravity radius factor value considerably more than changes in correlations. Portfolio managers and risk managers can use the new metric to identify correlation and volatility changes that dynamically react to new information.
PubDate: 2022-06-01

• Numerically Pricing Nonlinear Time-Fractional Black–Scholes Equation
with Time-Dependent Parameters Under Transaction Costs

Abstract: Abstract One of the assumptions of the classical Black–Scholes (B–S) is that the market is frictionless. Also, the classical B–S model cannot show the memory effect of the stock price in the financial markets. Previously, Ankudinova and Ehrhardt (Comput Math Appl 56:799–812, 2008) priced a European option under the classical B–S model with transaction costs when dividends are paid on assets during that period. But due to the importance of the trend memory effect in financial pricing, we extend Ankudinova’s and Ehrhardt’s study under the fractional B–S model when the price change of the underlying asset with time follows a fractal transmission system. The option price is governed by a time-fractional B–S equation of order $$0<\alpha <1$$ . The main objective of this study is to obtain a numerical solution to determine the European option price with transaction costs based on the implicit difference scheme. This difference scheme is unconditionally stable and convergent and is shown stability and convergence by Fourier analysis. Numerical results and comparisons demonstrate that the introduced difference scheme has high accuracy and efficiency.
PubDate: 2022-06-01

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762