Filters








126,777 Hits in 11.4 sec

Confronting Machine Learning With Financial Research [article]

Kristof Lommers, Ouns El Harzli, Jack Kim
2021 arXiv   pre-print
We discuss some of the main challenges of machine learning in finance and examine how these could be accounted for.  ...  Moreover, we discuss the various applications of machine learning in the research process such as estimation, empirical discovery, testing, causal inference and prediction.  ...  Markov-shifting models have been a popular regime switching framework for financial and economic time series.  ... 
arXiv:2103.00366v2 fatcat:bp4j34cenjf4lii5rgav5o5d6e

Tricks for Time Series [chapter]

Klaus-Robert Müller
2012 Lecture Notes in Computer Science  
In the last section we focus on tricks related to time series analysis and economic forecasting.  ...  As an alternative, the author presents several new smoothing regularizers for both feedforward and recurrent networks that empirically are found to work better.  ...  turning points in time series (p. 374).  ... 
doi:10.1007/978-3-642-35289-8_21 fatcat:xvasculgqzboponywvqp4jloke

Bid Prediction in Repeated Auctions with Learning [article]

Gali Noti, Vasilis Syrgkanis
2020 arXiv   pre-print
This portrays the importance of using structural econometric approaches in predicting how players will respond to changes in the market.  ...  We show that the no-regret econometric methods perform comparable to state-of-the-art time-series machine learning methods when there is no co-variate shift, but significantly outperform machine learning  ...  the machine-learning methods both in the task of predicting a series of future bids and in the task of predicting one step at every time.  ... 
arXiv:2007.13193v2 fatcat:ckcrbxdbnbeptbtrke34etozbe

Learning Leading Indicators for Time Series Predictions [article]

Magda Gregorova, Alexandros Kalousis, Stéphane Marchand-Maillet
2016 arXiv   pre-print
We consider the problem of learning models for forecasting multiple time-series systems together with discovering the leading indicators that serve as good predictors for the system.  ...  While the first method assumes common structures across the whole system, our second method uncovers model clusters based on the Granger-causality and leading indicators together with learning the model  ...  Our work builds on the standard regularized multi-task learning and structured regularization techniques developed outside the time-series settings.  ... 
arXiv:1507.01978v3 fatcat:awbeye5ghnfhja75lwbajo7p7u

Neural Network Predictive Modeling on Dynamic Portfolio Management—A Simulation-Based Portfolio Optimization Approach

Jiayang Yu, Kuo-Chu Chang
2020 Journal of Risk and Financial Management  
In this paper, we present a simulation-based approach by fusing a number of macroeconomic factors using Neural Networks (NN) to build an Economic Factor-based Predictive Model (EFPM).  ...  their portfolio performance in a timely manner.  ...  A number of simulated time series are generated for economic factors to combine the time-varying volatility, tail dependence structure, and sample mean together.  ... 
doi:10.3390/jrfm13110285 fatcat:qce2lcyp4zdobbo75iunlvlyum

P-V-L Deep: A Big Data Analytics Solution for Now-casting in Monetary Policy

Maryam Hajipour Sarduie, Mohammadali Afshar Kazemi, Mahmood Alborzi, Adel Azar, Ali Kermanshah
2020 Journal of Information Technology Management  
was used for unsupervised learning, data representation, and data reconstruction; moreover, long short-term memory was adopted in order to evaluate now-casting performance of deep nets in time-series  ...  In predictive analytics, the forecast of near-future and recent past - or in other words, the now-casting - is the continuous study of real-time events and constantly updated where it considers eventuality  ...  learning and to determine and evaluate the predicting performance of deep nets' macro-econometrics variables' time-series.  ... 
doi:10.22059/jitm.2020.293071.2429 doaj:97430d4a1eb04b2f9cc9be5597cd2b26 fatcat:waqwqypolra7zbcxyczuli2zci

Causality Learning from Time Series Data for the Industrial Finance Analysis via the Multi-dimensional Point Process

Liangliang Shi, Peili Lu, Junchi Yan
2020 Intelligent Automation and Soft Computing  
Causality learning has been an important tool for decision making, especially for financial analytics.  ...  The expectation-maximization algorithm is used for minimizing the negative loglikelihood with the regularization in order to avoid overfitting in the high dimension and will make the causal inference more  ...  The EM Algorithm Zhou et al. have proposed an EM-based learning method for low-rank and sparse regularizations.  ... 
doi:10.32604/iasc.2020.010121 fatcat:epwypuhuhrhz3ig25a7kgx7jsi

Machine learning methods in finance

Irina Karachun, Lyubov Vinnichek, Andrey Tuskov, S. Roshchupkin
2021 SHS Web of Conferences  
, logistic regression, and autoregressive time series models.  ...  This article focuses on supervised learning and reinforcement learning. These areas overlap most with econometrics, predictive modelling, and optimal control in finance.  ...  Machine learning focuses on finding structure in large data sets, and the main tools for predictor selection are regularization and dropout.  ... 
doi:10.1051/shsconf/202111005012 fatcat:fll3dsvghnfddab2mtkj7nuz4q

Analysis of Causality in Stock Market Data

Chathra Hendahewa, Vladimir Pavlovic
2012 2012 11th International Conference on Machine Learning and Applications  
While there is a rich literature in estimating implied and stochastic volatility in financial time series using traditional econometric methods, the application of machine learning methods such as sparse  ...  In this paper, we propose a sparse, smooth regularized regression model to infer the volatility of the data while explicitly accounting for dependencies between different companies.  ...  Estimation and Learning To estimate and learn the β w k coefficients for each company k for time window w specified in equation 4, Algorithm 1 is used and it defines how we tune the regularization terms  ... 
doi:10.1109/icmla.2012.56 dblp:conf/icmla/HendahewaP12 fatcat:fzbyzg4cpvdz3ovl2enggdsmeu

Container Volume Prediction Using Time-Series Decomposition with a Long Short-Term Memory Models

Eunju Lee, Dohee Kim, Hyerim Bae
2021 Applied Sciences  
The purpose of this study is to improve the prediction of container volumes in Busan ports by applying external variables and time-series data decomposition methods to deep learning prediction models.  ...  In this study, a novel deep learning prediction model is proposed that combines prediction and trend identification of container volume.  ...  Section 2 provides an overview of time-series analysis, deep learning prediction, and deep learning in container volume prediction.  ... 
doi:10.3390/app11198995 fatcat:xboky2pwo5h6lk3h6w64m2goiq

Using Elman Neural Network Model to Forecast and Analyze the Agricultural Economy

Congyou Yu, Miaochao Chen
2022 Journal of Mathematics  
To improve the accuracy of agricultural economic time series forecasting under the condition of complexity and diversity, this paper proposes an agricultural economic forecasting method based on Elman  ...  Secondly, this paper designs an efficient Elman neural network topology and sends the selected important data into the neural network for data learning and neural network parameter optimization, to achieve  ...  Elman neural network structure and its topological structure are mainly for processing nonlinear time series data. e characteristic of this type of network structure is that the data feedback connection  ... 
doi:10.1155/2022/8374696 fatcat:s275lafccbe4jlsjkonuqnfsva

Predictive Analysis of Economic Chaotic Time Series Based on Chaotic Genetics Combined with Fuzzy Decision Algorithm

Xiuge Tan, Wei Wang
2021 Complexity  
model for economic chaotic time series, performed parameter synchronization optimization and moderate function construction, analyzed the prediction processes of economic chaotic time series, conducted  ...  The irreversibility in time, the multicausality on lines, and the uncertainty of feedbacks make economic systems and the predictions of economic chaotic time series possess the characteristics of high  ...  In this way, the traditional algorithm for solving the embedded dimension and time delay is no longer suitable for the changed phase space structure, so a multistep prediction of economic chaotic time  ... 
doi:10.1155/2021/5517502 fatcat:ix3qqyos7bendfmtefzgc7qwva

Regularized Dynamic Self Organized Neural Network Inspired by the Immune Algorithm for Financial Time Series Prediction [chapter]

Haya Al-Askar, Abir Jaafar Hussain, Dhiya Al-Jumeily, Naeem Radi
2014 Lecture Notes in Computer Science  
In this work, the average values of 30 simulations generated from 10 financial time series are examined.  ...  The simulation results indicated that the proposed network showed average improvement using the annualized return for all signals of 0.491, 8.1899 and 1.0072 in comparison to the benchmarked networks,  ...  Modelling DSMIA for Financial Time Series Prediction: In this section the structure of the neural network models is explained.  ... 
doi:10.1007/978-3-319-09330-7_8 fatcat:vt5nquqok5bjhii6mx3dxcjlj4

Regularized dynamic self-organized neural network inspired by the immune algorithm for financial time series prediction

Abir Jaafar Hussain, Dhiya Al-Jumeily, Haya Al-Askar, Naeem Radi
2016 Neurocomputing  
In this work, the average values of 30 simulations generated from 10 financial time series are examined.  ...  The simulation results indicated that the proposed network showed average improvement using the annualized return for all signals of 0.491, 8.1899 and 1.0072 in comparison to the benchmarked networks,  ...  Modelling DSMIA for Financial Time Series Prediction: In this section the structure of the neural network models is explained.  ... 
doi:10.1016/j.neucom.2015.01.109 fatcat:n7f6vewv5zf35fjuhuvotppqlm

Neural Network Techniques for Time Series Prediction: A Review

Muhammad Faheem Mushtaq, Urooj Akram, Muhammad Aamir, Haseeb Ali, Muhammad Zulqarnain
2019 JOIV: International Journal on Informatics Visualization  
Neural Networks (NN) have appeared as an effective tool for forecasting of time series.  ...  The goal of this research is to present the reader awareness about HONN for physical time series prediction, to highlight some benefits and challenges using HONN.  ...  It creates the overfitting problem in the structure and needs more training time for learning.  ... 
doi:10.30630/joiv.3.3.281 fatcat:uhqrmqth35a6hkf26raf3rt7lu
« Previous Showing results 1 — 15 out of 126,777 results