Search

The search for an unbiased company valuation method to reduce uncertainty, whether or not it is automatic, has been a relevant topic in social sciences and business development for decades. Many methods have been described in the literature, but consensus has not been reached. In the companion paper we aimed to review the assessment capabilities of traditional company valuation model, based on company's intrinsic value using the Discounted Cash Flow (DCF). In this paper, we capitalized on the potential of exogenous information combined with Machine Learning (ML) techniques. To do so, we performed an extensive analysis to evaluate the predictive capabilities with up to 18 different ML techniques. Endogenous variables (features) related to value creation (DCF) were proved to be crucial elements for the models, while the incorporation of exogenous, industry/country specific ones, incrementally improves the ML performance. Bagging Trees, Supported Vector Machine Regression, Gaussian Process Regression methods consistently provided the best results. We concluded that an unbiased model can be created based on endogenous and exogenous information to build a reference framework, to price and benchmark Enterprise Value for valuation and credit risk assessment. [ABSTRACT FROM AUTHOR]

The goal of this paper is twofold. Firstly, a Siamese-twin random projection neural network (ST-RPNN) is proposed for unsupervised binary hashing of images and compared with state-of-the-art techniques. Secondly, a comparison between Hamming-distance-based retrieval and a proposed bagging trees retrieval (BT-retrieval) algorithm operating directly on the PCA features is made with respect to performance, storage and search time. The ST-RPNN is made of two identical random projection neural networks and is trained to produce similar binary codes for similar input image pairs and different binary codes otherwise. The learning process is divided into two steps: a fast sparse neurons selection algorithm followed by an unsupervised bagging trees algorithm to extract the compact required-length code. Moreover, a BT-retrieval algorithm is proposed in this paper as a fast retrieval tool that ranks the database with respect to a query without distance calculations. Furthermore, (BT-PCA) is a novel extension where the BT-retrieval is applied directly on the PCA features with a significantly lower time search than Hamming-distance-based approach. The proposed technique is compared with ten unsupervised image binary hashing techniques on the COREL1K dataset and the CIFAR10 dataset. The proposed technique obtained better precision–recall results than all compared techniques on the COREL1K dataset, and better than eight of them on the CIFAR10 dataset. [ABSTRACT FROM AUTHOR]

ABSTRACT The biases in the Global Circulation Models ( GCMs) are crucial for understanding future climate changes. Currently, most bias correction methodologies suffer from the assumption that model bias is stationary. This paper provides a non-stationary bias correction model, termed residual-based bagging tree ( RBT) model, to reduce simulation biases and to quantify the contributions of single models. Specifically, the proposed model estimates the residuals between individual models and observations, and takes the differences between observations and the ensemble mean into consideration during the model training process. A case study is conducted for 10 major river basins in Mainland China during different seasons. Results show that the proposed model is capable of providing accurate and stable predictions while including the non-stationarities into the modelling framework. Significant reductions in both bias and root mean squared error are achieved with the proposed RBT model, especially for the central and western parts of China. The proposed RBT model has consistently better performance in reducing biases when compared with the raw ensemble mean, the ensemble mean with simple additive bias correction, and the single best model for different seasons. Furthermore, the contribution of each single GCM in reducing the overall bias is quantified. The single model importance varies between 3.1% and 7.2%. For different future scenarios ( RCP 2.6, RCP 4.5, and RCP 8.5), the results from RBT model suggest temperature increases of 1.44, 2.59, and 4.71 °C by the end of the century, respectively, when compared with the average temperature during 1970-1999. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder (ASD) is a very complicated disorder; a recent study made in the USA showed that it is the second most widespread neurodevelopmental disorder among children. It is a highly undetectable disease since its symptoms are not the same for each child. The traditional detecting methods are not efficient especially in the early years of child development, resulting in late treatment. This paper proposes a machine learning approach that detects ASD through gene signature, at childbirth. The approach processes the data of blood-based gene expression of 21 ASD child and 63 Controls into a feature selection phase using Bagging Tree Algorithm, the delivered features are then weighted through the application of a genetic mathematical formula. A Discretization process is used before the main Association Rules process. The final association rules show the most important relationships between genes for the early prediction of the ASD. The rules showed relationships between 600 genes in which 8 genes are the most affecting ASD with an accuracy of 90%. [ABSTRACT FROM AUTHOR]

For cleaner and sustainable greenhouse crops production, it is essential to successfully manage the needs and resources. Thus the prediction of the greenhouse microclimate, especially the temperature and relative humidity is of great interest. The research done in this area is, however, still limited, and a number of machine learning techniques have not yet been sufficiently exploited. The objective of this paper is to evaluate two greenhouse modeling techniques (machine learning (Artificial Neural Networks (ANN), Support Vector Machine (SVM), Bagging trees (BG) and Boosting trees (BT)) and Computational Fluid Dynamics (CFD) methods and assess the impact of the seasonal changes on machine learning performances. The study was carried out in a commercial greenhouse located in Agadir, Morocco, and the experimental data were collected during October and March. Results show that all predictive models are capable of predicting the inside air temperature (Tin) and relative humidity (Rhin) of the greenhouse with a quite good precision (R>0.98, nRMSE0.98, nRMSE

Historically, observing snow depth over large areas has been difficult. When snow depth observations are sparse, regression models can be used to infer the snow depth over a given area. Data sparsity has also left many important questions about such inference unexamined. Improved inference, or estimation, of snow depth and its spatial distribution from a given set of observations can benefit a wide range of applications from water resource management, to ecological studies, to validation of satellite estimates of snow pack. The development of Light Detection and Ranging (LiDAR) technology has provided non-sparse snow depth measurements, which we use in this study, to address fundamental questions about snow depth inference using both sparse and non-sparse observations. For example, when are more data needed and when are data redundant? Results apply to both traditional and manual snow depth measurements and to LiDAR observations. Through sampling experiments on high-resolution LiDAR snow depth observations at six separate 1.17-km2 sites in the Colorado Rocky Mountains, we provide novel perspectives on a variety of issues affecting the regression estimation of snow depth from sparse observations. We measure the effects of observation count, random selection of observations, quality of predictor variables, and cross-validation procedures using three skill metrics: percent error in total snow volume, root mean squared error ( RMSE), and R2. Extremes of predictor quality are used to understand the range of its effect; how do predictors downloaded from internet perform against more accurate predictors measured by LiDAR? Whereas cross validation remains the only option for validating inference from sparse observations, in our experiments, the full set of LiDAR-measured snow depths can be considered the 'true' spatial distribution and used to understand cross-validation bias at the spatial scale of inference. We model at the 30-m resolution of readily available predictors, which is a popular spatial resolution in the literature. Three regression models are also compared, and we briefly examine how sampling design affects model skill. Results quantify the primary dependence of each skill metric on observation count that ranges over three orders of magnitude, doubling at each step from 25 up to 3200. Whereas uncertainty (resulting from random selection of observations) in percent error of true total snow volume is typically well constrained by 100-200 observations, there is considerable uncertainty in the inferred spatial distribution ( R2) even at medium observation counts (200-800). We show that percent error in total snow volume is not sensitive to predictor quality, although RMSE and R2 (measures of spatial distribution) often depend critically on it. Inaccuracies of downloaded predictors (most often the vegetation predictors) can easily require a quadrupling of observation count to match RMSE and R2 scores obtained by LiDAR-measured predictors. Under cross validation, the RMSE and R2 skill measures are consistently biased towards poorer results than their true validations. This is primarily a result of greater variance at the spatial scales of point observations used for cross validation than at the 30-m resolution of the model. The magnitude of this bias depends on individual site characteristics, observation count (for our experimental design), and sampling design. Sampling designs that maximize independent information maximize cross-validation bias but also maximize true R2. The bagging tree model is found to generally outperform the other regression models in the study on several criteria. Finally, we discuss and recommend use of LiDAR in conjunction with regression modelling to advance understanding of snow depth spatial distribution at spatial scales of thousands of square kilometres. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The task of modeling the distribution of a large number of tree species under future climate scenarios presents unique challenges. First, the model must be robust enough to handle climate data outside the current range without producing unacceptable instability in the output. In addition, the technique should have automatic search mechanisms built in to select the most appropriate values for input model parameters for each species so that minimal effort is required when these parameters are fine-tuned for individual tree species. We evaluated four statistical models—Regression Tree Analysis (RTA), Bagging Trees (BT), Random Forests (RF), and Multivariate Adaptive Regression Splines (MARS)—for predictive vegetation mapping under current and future climate scenarios according to the Canadian Climate Centre global circulation model. To test, we applied these techniques to four tree species common in the eastern United States: loblolly pine ( Pinus taeda), sugar maple ( Acer saccharum), American beech ( Fagus grandifolia), and white oak ( Quercus alba). When the four techniques were assessed with Kappa and fuzzy Kappa statistics, RF and BT were superior in reproducing current importance value (a measure of basal area in addition to abundance) distributions for the four tree species, as derived from approximately 100,000 USDA Forest Service’s Forest Inventory and Analysis plots. Future estimates of suitable habitat after climate change were visually more reasonable with BT and RF, with slightly better performance by RF as assessed by Kappa statistics, correlation estimates, and spatial distribution of importance values. Although RTA did not perform as well as BT and RF, it provided interpretive models for species whose distributions were captured well by our current set of predictors. MARS was adequate for predicting current distributions but unacceptable for future climate. We consider RTA, BT, and RF modeling approaches, especially when used together to take advantage of their individual strengths, to be robust for predictive mapping and recommend their inclusion in the ecological toolbox. [ABSTRACT FROM AUTHOR]