Evolution of the IBEX-35 vs other international indices: determinants of market value according to XGBOOST and GLM models

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Juián Martínez-Vargas ◽  
Pedro Carmona ◽  
Pol Torrelles
Keyword(s):  
Market Value ◽  
Financial Statements ◽  
Share Price ◽  
Price Formation ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Political Factors ◽  
Content Type ◽  
International Trends ◽  
Extreme Gradient Boosting

PurposeThe purpose of this paper is to study the influence of different quantitative (traditionally used) and qualitative variables, such as the possible negative effect in determined periods of certain socio-political factors on share price formation.Design/methodology/approachWe first analyse descriptively the evolution of the Ibex-35 in recent years and compare it with other international benchmark indices. Bellow, two techniques have been compared: a classic linear regression statistical model (GLM) and a method based on machine learning techniques called Extreme Gradient Boosting (XGBoost).FindingsXGBoost yields a very accurate market value prediction model that clearly outperforms the other, with a coefficient of determination close to 90%, calculated on validation sets.Practical implicationsAccording to our analysis, individual accounts are equally or more important than consolidated information in predicting the behaviour of share prices. This would justify Spain maintaining the obligation to present individual interim financial statements, which does not happen in other European Union countries because IAS 34 only stipulates consolidated interim financial statements.Social implicationsThe descriptive analysis allows us to see how the Ibex-35 has moved away from international trends, especially in periods in which some relevant socio-political events occurred, such as the independence referendum in Catalonia, the double elections of 2019 or the early handling of the Covid-19 pandemic in 2020.Originality/valueCompared to other variables, the XGBoost model assigns little importance to socio-political factors when it comes to share price formation; however, this model explains 89.33% of its variance.

scholarly journals A Machine Learning Method for Predicting Vegetation Indices in China

2021 ◽  
Vol 13 (6) ◽  
pp. 1147
Author(s):  
Xiangqian Li ◽  
Wenping Yuan ◽  
Wenjie Dong
Keyword(s):  
Machine Learning ◽  
Growing Season ◽  
Crop Growth ◽  
Spatiotemporal Distribution ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Severe Drought ◽  
Vegetation Growth ◽  
Extreme Gradient Boosting ◽  
Boosting Method

To forecast the terrestrial carbon cycle and monitor food security, vegetation growth must be accurately predicted; however, current process-based ecosystem and crop-growth models are limited in their effectiveness. This study developed a machine learning model using the extreme gradient boosting method to predict vegetation growth throughout the growing season in China from 2001 to 2018. The model used satellite-derived vegetation data for the first month of each growing season, CO2 concentration, and several meteorological factors as data sources for the explanatory variables. Results showed that the model could reproduce the spatiotemporal distribution of vegetation growth as represented by the satellite-derived normalized difference vegetation index (NDVI). The predictive error for the growing season NDVI was less than 5% for more than 98% of vegetated areas in China; the model represented seasonal variations in NDVI well. The coefficient of determination (R2) between the monthly observed and predicted NDVI was 0.83, and more than 69% of vegetated areas had an R2 > 0.8. The effectiveness of the model was examined for a severe drought year (2009), and results showed that the model could reproduce the spatiotemporal distribution of NDVI even under extreme conditions. This model provides an alternative method for predicting vegetation growth and has great potential for monitoring vegetation dynamics and crop growth.

scholarly journals Modeling of nitrogen solubility in normal alkanes using machine learning methods compared with cubic and PC-SAFT equations of state

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Seyed Ali Madani ◽  
Mohammad-Reza Mohammadi ◽  
Saeid Atashrouz ◽  
Ali Abedi ◽  
Abdolhossein Hemmati-Sarapardeh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Weight ◽  
Oil Recovery ◽  
Equations Of State ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Operating Pressure ◽  
Normal Alkanes ◽  
Light Gradient ◽  
Extreme Gradient Boosting

AbstractAccurate prediction of the solubility of gases in hydrocarbons is a crucial factor in designing enhanced oil recovery (EOR) operations by gas injection as well as separation, and chemical reaction processes in a petroleum refinery. In this work, nitrogen (N2) solubility in normal alkanes as the major constituents of crude oil was modeled using five representative machine learning (ML) models namely gradient boosting with categorical features support (CatBoost), random forest, light gradient boosting machine (LightGBM), k-nearest neighbors (k-NN), and extreme gradient boosting (XGBoost). A large solubility databank containing 1982 data points was utilized to establish the models for predicting N2 solubility in normal alkanes as a function of pressure, temperature, and molecular weight of normal alkanes over broad ranges of operating pressure (0.0212–69.12 MPa) and temperature (91–703 K). The molecular weight range of normal alkanes was from 16 to 507 g/mol. Also, five equations of state (EOSs) including Redlich–Kwong (RK), Soave–Redlich–Kwong (SRK), Zudkevitch–Joffe (ZJ), Peng–Robinson (PR), and perturbed-chain statistical associating fluid theory (PC-SAFT) were used comparatively with the ML models to estimate N2 solubility in normal alkanes. Results revealed that the CatBoost model is the most precise model in this work with a root mean square error of 0.0147 and coefficient of determination of 0.9943. ZJ EOS also provided the best estimates for the N2 solubility in normal alkanes among the EOSs. Lastly, the results of relevancy factor analysis indicated that pressure has the greatest influence on N2 solubility in normal alkanes and the N2 solubility increases with increasing the molecular weight of normal alkanes.

scholarly journals Random forest and extreme gradient boosting algorithms for streamflow modeling using vessel features, and tree-rings

2021 ◽  
Author(s):  
Hossein Sahour ◽  
Vahid Gholami ◽  
Javad Torkman ◽  
Mehdi Vazifedan ◽  
Sirwe Saeedi
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Tree Rings ◽  
Test Site ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Growing Seasons ◽  
Extreme Gradient Boosting ◽  
Streamflow Modeling

Abstract Monitoring temporal variation of streamflow is necessary for many water resources management plans, yet, such practices are constrained by the absence or paucity of data in many rivers around the world. Using a permanent river in the north of Iran as a test site, a machine learning framework was proposed to model the streamflow data in the three periods of growing seasons based on tree-rings and vessel features of the Zelkova carpinifolia species. First, full-disc samples were taken from 30 trees near the river, and the samples went through preprocessing, cross-dating, standardization, and time series analysis. Two machine learning algorithms, namely random forest (RF) and extreme gradient boosting (XGB), were used to model the relationships between dendrochronology variables (tree-rings and vessel features in the three periods of growing seasons) and the corresponding streamflow rates. The performance of each model was evaluated using statistical coefficients (coefficient of determination (R-squared), Nash-Sutcliffe efficiency (NSE), and root-mean-square error (NRMSE)). Findings demonstrate that consideration should be given to the XGB model in streamflow modeling given its apparent enhanced performance (R-squared: 0.87; NSE: 0.81; and NRMSE: 0.43) over the RF model (R-squared: 0.82; NSE: 0.71; and NRMSE: 0.52). Further, the results showed that the models perform better in modeling the normal and low flows compared to extremely high flows. Finally, the tested models were used to reconstruct the temporal streamflow during the past decades (1970–1981).

scholarly journals An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

Minerals ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 487
Author(s):  
Maciej Rzychoń ◽  
Alina Żogała ◽  
Leokadia Róg
Keyword(s):  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Important Indicator ◽  
Upper Silesian Coal Basin ◽  
Proposed Model ◽  
Extreme Gradient Boosting ◽  
The Impact ◽  
Partial Dependence ◽  
Individual Input

The hemispherical temperature (HT) is the most important indicator representing ash fusion temperatures (AFTs) in the Polish industry to assess the suitability of coal for combustion as well as gasification purposes. It is important, for safe operation and energy saving, to know or to be able to predict value of this parameter. In this study a non-linear model predicting the HT value, based on ash oxides content for 360 coal samples from the Upper Silesian Coal Basin, was developed. The proposed model was established using the machine learning method—extreme gradient boosting (XGBoost) regressor. An important feature of models based on the XGBoost algorithm is the ability to determine the impact of individual input parameters on the predicted value using the feature importance (FI) technique. This method allowed the determination of ash oxides having the greatest impact on the projected HT. Then, the partial dependence plots (PDP) technique was used to visualize the effect of individual oxides on the predicted value. The results indicate that proposed model could estimate value of HT with high accuracy. The coefficient of determination (R2) of the prediction has reached satisfactory value of 0.88.

Long-run causal nexus between share price and dividend

2014 ◽  
Vol 8 (2) ◽  
pp. 136-145 ◽  
Author(s):  
P.S. Nirmala ◽  
P.S. Sanju ◽  
M. Ramachandran
Keyword(s):  
Unit Root ◽  
Dividend Policy ◽  
Investment Decisions ◽  
Market Value ◽  
Share Price ◽  
Indian Market ◽  
Causal Relations ◽  
Content Type ◽  
Share Prices ◽  
Long Run

Purpose – The purpose of this paper was to examine the long-run causal relations between share price and dividend in the Indian market. Design/methodology/approach – Panel vector error correction model is estimated to examine the long-run causal relations between share price and dividend. Prior to this, panel unit root tests and panel cointegration tests are carried out to test the unit root properties of the data and test for the existence of long-run cointegrating relationship between the variables, respectively. Findings – The results of empirical investigation reveal that there exists bi-directional long-run causality between share price and dividends. Research limitations/implications – For the chosen sample, data on share price are available only for limited years. This limits the time dimension of the sample. Hence, in the future, the analysis can be extended to cover longer time series. Practical implications – The interplay between share prices and dividends needs to be given due consideration by firms while framing their policies. A change in dividend policy would have an effect on the market value of the firm; hence, firms need to frame dividend policy in such a way that it would enhance their market value. Similarly, investors need to take into consideration the influence of share prices and dividends on each other. While making investment decisions, they need to consider the dividend history of shares, as better dividends would lead to better share prices. Originality/value – To the best of the authors' knowledge, this study is the first attempt in the Indian market to examine the long-run causal relations between share price and dividend. The results of this study would be helpful to the investors in taking wise investment decisions. It would also enable firms in formulating appropriate dividend policies.

A data mining approach for lubricant-based fault diagnosis

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
James Wakiru ◽  
Liliane Pintelon ◽  
Peter Muchiri ◽  
Peter Chemweno
Keyword(s):  
Decision Support ◽  
Fault Diagnosis ◽  
Knowledge Discovery ◽  
Predictive Accuracy ◽  
Principal Component ◽  
Gradient Boosting ◽  
Data Set ◽  
Content Type ◽  
Embedded Knowledge ◽  
Extreme Gradient Boosting

PurposeThe purpose of this paper is to develop a maintenance decision support system (DSS) framework using in-service lubricant data for fault diagnosis. The DSS reveals embedded patterns in the data (knowledge discovery) and automatically quantifies the influence of lubricant parameters on the unhealthy state of the machine using alternative classifiers. The classifiers are compared for robustness from which decision-makers select an appropriate classifier given a specific lubricant data set.Design/methodology/approachThe DSS embeds a framework integrating cluster and principal component analysis, for feature extraction, and eight classifiers among them extreme gradient boosting (XGB), random forest (RF), decision trees (DT) and logistic regression (LR). A qualitative and quantitative criterion is developed in conjunction with practitioners for comparing the classifier models.FindingsThe results show the importance of embedded knowledge, explored via a knowledge discovery approach. Moreover, the efficacy of the embedded knowledge on maintenance DSS is emphasized. Importantly, the proposed framework is demonstrated as plausible for decision support due to its high accuracy and consideration of practitioners needs.Practical implicationsThe proposed framework will potentially assist maintenance managers in accurately exploiting lubricant data for maintenance DSS, while offering insights with reduced time and errors.Originality/valueAdvances in lubricant-based intelligent approach for fault diagnosis is seldom utilized in practice, however, may be incorporated in the information management systems offering high predictive accuracy. The classification models' comparison approach, will inevitably assist the industry in selecting amongst divergent models' for DSS.

scholarly journals A Study on Economic Value Added and Share Price Behaviour: The Recent Analysis

2014 ◽  
pp. 115-130
Author(s):  
EMMANUEL ATTAH KUMAH
Keyword(s):  
Economic Value ◽  
Value Added ◽  
Market Value ◽  
Share Price ◽  
Coefficient Of Determination ◽  
Economic Value Added ◽  
Share Prices ◽  
Financial Variables ◽  
Almost All ◽  
The Relationship

Many companies seem to have destroyed shareholder's wealth over a period of time and only a few have positively contributed to their wealth. With the help of Economic Value Added (EVA) and Market Value Added (MVA) which tell what the institution is doing with investor's hard earned money, this research examines the relationship between the share price and other economic and financial variables such as Economic Value Added (EVA), Return on Asset (ROA) and Return on Fund (ROF). The overriding message of this paper is that the share price has direct correlation between the economic and financial variables. This analysis helps us to dig below the surface numbers to tell us more about the underlying business and whether there is a prima facie case for using EVA as one of the ranges of performance measurement tools. The relationship between EVA and other traditional measures is examined using Pearson's Coefficient of Correlation. Regression analysis has been used to examine the relationship of EVA, Earning Per Share (EPS), ROA and ROF with share price. The study found that, investing in the market is becoming more and more risky as the beta of the individual securities is increasing year by year. The increase in beta is due to increasing weighted average cost of capital; it specifies that capital is becoming more and more costly; Majority of the banks are increasing their capital to meet the increased expenses. As the market is becoming more and more risky, investors' expectations are increasing and therefore share prices of almost all the banks for almost all the years showed an increasing trend. Data analysis of 39 banks shows that: Share prices of two banks' shows high correlation of coefficient and coefficient of determination with EVA and share prices of eighteen banks' shows low correlation of coefficient and coefficient of determination with EVA. This specifies that there is no relationship between EVA and share price. Keywords: Economic Value, Financial Variables, Share Price, Behaviour and Market Value.

scholarly journals ANALISIS PENGARUH RASIO KEUANGAN TERHADAP HARGA SAHAM PADA PERUSAHAAN INDUSTRI BARANG KONSUMSI YANG TERDAFTAR DI BEI

2020 ◽  
Vol 1 (1) ◽  
pp. 268-274
Author(s):  
Melisa Yuana ◽  
Taudlikhul Afkar
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Consumer Goods ◽  
Stock Prices ◽  
Quantitative Method ◽  
Secondary Data ◽  
Financial Statements ◽  
Share Price ◽  
Coefficient Of Determination ◽  
Significant Variable

The purpose for this study to analyze also study the presence or absence of financial ratios that contribut to stock prices. The population in this study is the financial statements of consumer goods industry companies that are listed on the IDX. The study used 36 samples from 6 consumer goods companies with a reporting period of 6 years. Secondary data is a type of data in this study. The method or method used is the quantitative method, where data are analyzed with the classic assumption test, multiple linear regression, also the coefficient of determination. The research carried out resulted in a significant variable influencing the share price of ROA and EPS. Whereas CR, DER, and TATO had no significant effect on stock prices.

scholarly journals Pengaruh Return On Asset (ROA) Dan Return On Equity (ROE) Terhadap Harga Saham Pada Perusahaan Manufaktur yang Terdaftar di Indonesia Periode 2017-2019

2021 ◽  
Vol 4 (1) ◽  
pp. 20
Author(s):  
Mahdi Hendrich
Keyword(s):  
Stock Prices ◽  
Stock Exchange ◽  
Sampling Technique ◽  
Financial Statements ◽  
Share Price ◽  
Coefficient Of Determination ◽  
State Variables ◽  
Manufacturing Companies ◽  
Return On Equity ◽  
Positive Effect

This study attempts to examine how much influence these two variables, namely ROA and ROE, on stock prices, especially in manufacturing companies of the type of "Consumer Goods" listed on the Indonesia Stock Exchange, the Malaysia Stock Exchange and the Thailand Stock Exchange. The sampling technique used was purposive sampling based on certain criteria or considerations. The sample taken is the financial statements of 9 companies that have been determined in accordance with the provisions of sampling with the period 2017-2019. The result shows that, simultaneously, Return On Asset (ROA) and Return On Equity (ROE) have a positive effect on stock prices in manufacturing companies in Indonesia. The coefficient of determination (R2) of 0.238 indicates that each share price is influenced by the ROA, ROE and State variables of 23.8% while the remaining 76.2% is influenced by other variables not examined.

Predicting the inpatient hospital cost using a machine learning approach

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Suraj Kulkarni ◽  
Suhas Suresh Ambekar ◽  
Manoj Hudnurkar
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Random Forest ◽  
Insurance Companies ◽  
Hospital Charges ◽  
Categorical Variables ◽  
Gradient Boosting ◽  
Content Type ◽  
Total Cost ◽  
Extreme Gradient Boosting

Purpose Increasing health-care costs are a major concern, especially in the USA. The purpose of this paper is to predict the hospital charges of a patient before being admitted. This will help a patient who is getting admitted: “electively” can plan his/her finance. Also, this can be used as a tool by payers (insurance companies) to better forecast the amount that a patient might claim. Design/methodology/approach This research method involves secondary data collected from New York state’s patient discharges of 2017. A stratified sampling technique is used to sample the data from the population, feature engineering is done on categorical variables. Different regression techniques are being used to predict the target value “total charges.” Findings Total cost varies linearly with the length of stay. Among all the machine learning algorithms considered, namely, random forest, stochastic gradient descent (SGD) regressor, K nearest neighbors regressor, extreme gradient boosting regressor and gradient boosting regressor, random forest regressor had the best accuracy with R2 value 0.7753. “Age group” was the most important predictor among all the features. Practical implications This model can be helpful for patients who want to compare the cost at different hospitals and can plan their finances accordingly in case of “elective” admission. Insurance companies can predict how much a patient with a particular medical condition might claim by getting admitted to the hospital. Originality/value Health care can be a costly affair if not planned properly. This research gives patients and insurance companies a better prediction of the total cost that they might incur.

Sign in / Sign up

Export Citation Format

Share Document