scholarly journals Study on the Effectiveness of the Investment Strategy Based on a Classifier with Rules Adapted by Machine Learning

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
A. Wiliński ◽  
A. Bera ◽  
W. Nowicki ◽  
P. Błaszyński
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Parameter Space ◽  
Cross Validation ◽  
Investment Decision ◽  
Investment Strategy ◽  
Time Varying ◽  
Time Varying Parameters ◽  
Rule Set ◽  
The Relationship

This paper examines two transactional strategies based on the classifier which opens positions using some rules and closes them using different rules. A rule set contains time-varying parameters that when matched allow making an investment decision. Researches contain the study of variability of these parameters and the relationship between learning period and testing (using the learned parameters). The strategies are evaluated based on the time series of cumulative profit achieved in the test periods. The study was conducted on the most popular currency pair EURUSD (Euro-Dollar) sampled with interval of 1 hour. An important contribution to the theory of algotrading resulting from presented research is specification of the parameter space (quite large, consisting of 11 parameters) that achieves very good results using cross validation.

scholarly journals An Extended Time Series Algorithm for Modal Identification from Nonstationary Ambient Response Data Only

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Chang-Sheng Lin ◽  
Dar-Yun Chiang ◽  
Tse-Chuan Tseng
Keyword(s):  
Time Series ◽  
Arma Model ◽  
Identification Problem ◽  
Nonstationary Time Series ◽  
Modal Identification ◽  
Ambient Vibration ◽  
Time Varying ◽  
Varying Parameters ◽  
Response Data ◽  
Time Varying Parameters

Modal Identification is considered from response data of structural systems under nonstationary ambient vibration. The conventional autoregressive moving average (ARMA) algorithm is applicable to perform modal identification, however, only for stationary-process vibration. The ergodicity postulate which has been conventionally employed for stationary processes is no longer valid in the case of nonstationary analysis. The objective of this paper is therefore to develop modal-identification techniques based on the nonstationary time series for linear systems subjected to nonstationary ambient excitation. Nonstationary ARMA model with time-varying parameters is considered because of its capability of resolving general nonstationary problems. The parameters of moving averaging (MA) model in the nonstationary time-series algorithm are treated as functions of time and may be represented by a linear combination of base functions and therefore can be used to solve the identification problem of time-varying parameters. Numerical simulations confirm the validity of the proposed modal-identification method from nonstationary ambient response data.

scholarly journals A spatiotemporal ensemble machine learning framework for generating land use / land cover time-series maps for Europe (2000 – 2019) based on LUCAS, CORINE and GLAD Landsat

2021 ◽  
Author(s):  
Martijn Witjes ◽  
Leandro Parente ◽  
Chris J. van Diemen ◽  
Tomislav Hengl ◽  
Martin Landa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Land Use ◽  
Time Series ◽  
Land Cover ◽  
Data Science ◽  
Cross Validation ◽  
Series Data ◽  
Land Use Land Cover ◽  
Cover Time ◽  
Learning Framework

Abstract A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of land use / land cover (LULC) dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal covariate datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model was fitted by combining random forest, gradient boosted trees, and artificial neural network, with logistic regressor as meta-learner. The results show that the most important covariates for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with 62%, 70%, and 87% accuracy when predicting 33 (level-3), 14 (level-2), and 5 classes (level-1); with artificial surface classes such as 'airports' and 'railroads' showing the lowest match with validation points. The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest gradual deforestation trends in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer.

Optimal Investment Decision of the Recycle Economic Projects Based on Game Options

2011 ◽  
Vol 474-476 ◽  
pp. 315-319
Author(s):  
Hua Wang ◽  
Ling Ling Chen
Keyword(s):  
Investment Decision ◽  
Optimal Investment ◽  
Investment Strategy ◽  
Critical Value ◽  
Document Code ◽  
Game Options ◽  
Oligopoly Competition ◽  
The Relationship ◽  
The Value Function ◽  
Rate Research

In this paper, apply option game theory methods compensate for the inherent limitations of traditional NPV, derived the optimal preempt invest cycle economic projects critical value and the expression of the value function in under incomplete information oligopoly competition, give investors the preempt investment strategy rules, and analyze the relationship between critical value of investment and risks rate. Research shows that the larger face risk of being the first to competitors, the more investors will invest earlier. <b>CLC</b><b>：</b>F424.7 <b>Document code</b><b>：</b>A

scholarly journals A Dirichlet Autoregressive Model for the Analysis of Microbiota Time-Series Data

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
I. Creus-Martí ◽  
A. Moya ◽  
F. J. Santonja
Keyword(s):  
Time Series ◽  
Maximum Likelihood ◽  
Autoregressive Model ◽  
Time Series Data ◽  
Series Data ◽  
High Dimensional ◽  
Time Varying ◽  
Proposed Model ◽  
Time Varying Parameters

Growing interest in understanding microbiota dynamics has motivated the development of different strategies to model microbiota time series data. However, all of them must tackle the fact that the available data are high-dimensional, posing strong statistical and computational challenges. In order to address this challenge, we propose a Dirichlet autoregressive model with time-varying parameters, which can be directly adapted to explain the effect of groups of taxa, thus reducing the number of parameters estimated by maximum likelihood. A strategy has been implemented which speeds up this estimation. The usefulness of the proposed model is illustrated by application to a case study.

scholarly journals A spatiotemporal ensemble machine learning framework for generating land use / land cover time-series maps for Europe (2000 – 2019) based on LUCAS, CORINE and GLAD Landsat

2021 ◽  
Author(s):  
Martijn Witjes ◽  
Leandro Parente ◽  
Chris J. van Diemen ◽  
Tomislav Hengl ◽  
Martin Landa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Land Cover ◽  
Data Science ◽  
Cross Validation ◽  
Series Data ◽  
Cover Time ◽  
Learning Framework ◽  
Tree Classifier

Abstract A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of long-term LULC dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including 5~million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model consists of a random forest, gradient boosted tree classifier, and a artificial neural network, with a logistic regressor as meta-learner. The results show that the most important variables for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, long-term surface water probability, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with overall accuracy (weighted F1-score) of 0.49, 0.63, and 0.83 when predicting 44 (level-3), 14 (level-2), and 5 classes (level-1). The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest forest loss in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer. Functions used to prepare data and run modeling are available via the eumap library for python.

scholarly journals A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data

Scientifica ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Ram C. Sharma ◽  
Keitarou Hara ◽  
Hidetake Hirayama
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Cross Validation ◽  
Coniferous Forest ◽  
Ground Truth ◽  
Model Parameters ◽  
Broadleaf Forest ◽  
Ground Truth Data ◽  
Supervised Classifiers ◽  
Performance And Evaluation

This paper presents the performance and evaluation of a number of machine learning classifiers for the discrimination between the vegetation physiognomic classes using the satellite based time-series of the surface reflectance data. Discrimination of six vegetation physiognomic classes, Evergreen Coniferous Forest, Evergreen Broadleaf Forest, Deciduous Coniferous Forest, Deciduous Broadleaf Forest, Shrubs, and Herbs, was dealt with in the research. Rich-feature data were prepared from time-series of the satellite data for the discrimination and cross-validation of the vegetation physiognomic types using machine learning approach. A set of machine learning experiments comprised of a number of supervised classifiers with different model parameters was conducted to assess how the discrimination of vegetation physiognomic classes varies with classifiers, input features, and ground truth data size. The performance of each experiment was evaluated by using the 10-fold cross-validation method. Experiment using the Random Forests classifier provided highest overall accuracy (0.81) and kappa coefficient (0.78). However, accuracy metrics did not vary much with experiments. Accuracy metrics were found to be very sensitive to input features and size of ground truth data. The results obtained in the research are expected to be useful for improving the vegetation physiognomic mapping in Japan.

Adapting to the COVID-19 Pandemic

2021 ◽  
Vol 111 ◽  
pp. 351-355
Author(s):  
Michael Droste ◽  
James H. Stock
Keyword(s):  
Time Variation ◽  
Economic Activity ◽  
Behavioral Response ◽  
Significant Variation ◽  
Sir Model ◽  
Time Varying ◽  
Risk Of Infection ◽  
Varying Parameters ◽  
Time Varying Parameters ◽  
The Relationship

From early in the COVID-19 pandemic, economists have stressed the importance of individuals endogenously changing their behavior to reduce their risk of infection. This paper quantifies time variation in the endogenous behavioral response of economic activity to the prevalence of the virus using an estimated behavioral SIR model with time-varying parameters. We find significant variation in both the relationship between economic activity and viral prevalence and the relationship between transmissibility and economic activity. This variation reflects adaptation to the pandemic and has implications both for specification of behavioral SIR models and for the next stage of the pandemic.

scholarly journals Characterizing Phase Behavior Through Time-Varying Microarchitecture Independent Characteristics Clustering

2020 ◽  
Author(s):  
Rafael Soares ◽  
Rodolfo Azevedo
Keyword(s):  
Time Series ◽  
Phase Behavior ◽  
Multivariate Time Series ◽  
Source Code ◽  
Time Varying ◽  
Key Factors ◽  
Centrality Measure ◽  
Automatic Discovery ◽  
The Relationship

Programs often exhibit repeating behaviors, which are known as program phases. The automatic discovery of such structured behavior has benefited many applications. However, many existing phase signatures lack the ability to reason about what are the key factors of each phase. Also, programs exhibit phase behavior at many different granularities, and some exhibit hierarchical phase behavior. Many techniques focus on a single granularity, which can cause an out of sync classification with the actual phase behavior. We solve these problems by adopting a recently proposed method of subsequence clustering of multivariate time series. Using this method, the phases started to have a much more interpretable signature (MRF). We graphically showed that the method partitions the execution into a temporally consistent way. We showed the effectiveness of MRF&apos;s signature by using a centrality measure to identify the most important characteristics within a program phase. Finally, we present a case study to show the relationship between the MRF signature and source code.

Sign in / Sign up

Export Citation Format

Share Document