Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced b...Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.展开更多
α-diversity describes species diversity at local scales.The Simpson’s and Shannon-Wiener indices are widely used to characterizeα-diversity based on species abundances within a fixed study site(e.g.,a quadrat or pl...α-diversity describes species diversity at local scales.The Simpson’s and Shannon-Wiener indices are widely used to characterizeα-diversity based on species abundances within a fixed study site(e.g.,a quadrat or plot).Although such indices provide overall diversity estimates that can be analyzed,their values are not spatially continuous nor applicable in theory to any point within the study region,and thus they cannot be treated as spatial covariates for analyses of other variables.Herein,we extended the Simpson’s and Shannon-Wiener indices to create point estimates ofα-diversity for any location based on spatially explicit species occurrences within different bandwidths(i.e.,radii,with the location of interest as the center).For an arbitrary point in the study region,species occurrences within the circle plotting the bandwidth were weighted according to their distance from the center using a tri-cube kernel function,with occurrences closer to the center having greater weight than more distant ones.These novel kernel-basedα-diversity indices were tested using a tree dataset from a 400 m×400 m study region comprising a 200 m×200 m core region surrounded by a 100-m width buffer zone.Our newly extendedα-diversity indices did not disagree qualitatively with the traditional indices,and the former were slightly lower than the latter by<2%at medium and large band widths.The present work demonstrates the feasibility of using kernel-basedα-diversity indices to estimate diversity at any location in the study region and allows them to be used as quantifiable spatial covariates or predictors for other dependent variables of interest in future ecological studies.Spatially continuousα-diversity indices are useful to compare and monitor species trends in space and time,which is valuable for conservation practitioners.展开更多
文摘Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.
基金supported by Natural Science Foundation of Xinjiang Uygur Autonomous Region(2022D01A213)。
文摘α-diversity describes species diversity at local scales.The Simpson’s and Shannon-Wiener indices are widely used to characterizeα-diversity based on species abundances within a fixed study site(e.g.,a quadrat or plot).Although such indices provide overall diversity estimates that can be analyzed,their values are not spatially continuous nor applicable in theory to any point within the study region,and thus they cannot be treated as spatial covariates for analyses of other variables.Herein,we extended the Simpson’s and Shannon-Wiener indices to create point estimates ofα-diversity for any location based on spatially explicit species occurrences within different bandwidths(i.e.,radii,with the location of interest as the center).For an arbitrary point in the study region,species occurrences within the circle plotting the bandwidth were weighted according to their distance from the center using a tri-cube kernel function,with occurrences closer to the center having greater weight than more distant ones.These novel kernel-basedα-diversity indices were tested using a tree dataset from a 400 m×400 m study region comprising a 200 m×200 m core region surrounded by a 100-m width buffer zone.Our newly extendedα-diversity indices did not disagree qualitatively with the traditional indices,and the former were slightly lower than the latter by<2%at medium and large band widths.The present work demonstrates the feasibility of using kernel-basedα-diversity indices to estimate diversity at any location in the study region and allows them to be used as quantifiable spatial covariates or predictors for other dependent variables of interest in future ecological studies.Spatially continuousα-diversity indices are useful to compare and monitor species trends in space and time,which is valuable for conservation practitioners.
