Modeling the cost of energy in public sector buildings by linear regression and deep learning

Zekić–Sušac, Marijana; Knežević, Marinela; Scitovski, Rudolf

doi:10.1007/s10100-019-00643-y

Cited by 9 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 1980s, prediction with the data of health insurance became a research topic [11]. One of the most common statistical process methods that are typically used to predict and forecast healthcare costs is regression analysis [13][14][15][16]. In this project, a linear regression will be used to find if there any relationship among variables [17][18].…”

Section: Methodsmentioning

confidence: 99%

Healthcare cost prediction based on multifactorial linear regression

2022

International Conference on Biomedical and Intelligent Systems (IC-BIS 2022)

View full text Add to dashboard Cite

In general, healthcare spending mainly refers to medical insurance, which keeps raising from 1970 to 2020. Therefore, it is crucial to predict the costs accurately. Based on the multivariate linear regression, this paper constructs a quantitative model to investigate the cost of medical care. The data used for research were gathered from Massachusetts health insurance centre. To avoid overfitting effects and simplify the model, only parts of the variables were chosen for prediction model. In the research, the Y variable was changed into log(y), and all X variables were used to fit a linear regression model. According to the analysis, the healthcare cost has a significant relationship with smoking. These results shed light on guiding further research exploring the healthcare cost.

show abstract

Section: Methodsmentioning

confidence: 99%

Healthcare cost prediction based on multifactorial linear regression

2022

International Conference on Biomedical and Intelligent Systems (IC-BIS 2022)

View full text Add to dashboard Cite

show abstract

“…the residual sum of squares (RSS) is significantly lower in the full model as compared to the reduced model. A partial F-test is used in this study to compare the SSE of the full and reduced models to see if there has been a remarkable change in SSE due to the removal of a term and hence a significant change in how well the model fits or predicts the observed data [196,197]. In general, when the model includes the moderating variable of (CSRD * institutional owner), the results of the partial F-test show that R-square and residual standard error (RSE) are 0.6716 and 1.521, while the results of R-square and RSE for the reduced model excluding the moderation variable are 0.6708 and 1.522.…”

Section: Partial F-testmentioning

confidence: 99%

Corporate Social Responsibility Disclosure (CSRD) and Financial Distressed Risk (FDR): Does Institutional Ownership Matter?

et al. 2022

View full text Add to dashboard Cite

This study aims to investigate the effect of corporate social responsibility disclosure (CSRD) on financial distressed risk (FDR) among firms listed on the Tehran Stock Exchange (TSE). This paper also examines whether there is a negative linkage between institutional ownership as a corporate governance mechanism and corporate bankruptcy. The final research purpose is to analyze if there is a moderating effect of institutional owners on the relationship between CSRD and FDR too. The study sample consists of 200 firms listed on the TSE between 2013 and 2018, and the statistical model is logistic regression. When FDR is assessed under both Article 141 of Iran’s business law and the Altman Z-score model, our results on the main research hypotheses are quite similar. Considering the social and cultural conditions and economic situation of the Iranian market, the results show that firms with a high level of CSR disclosure are not able to make themselves more creditworthy and do not have better access to financing, resulting in more financial insolvency. Our findings confirm institutional shareholders play a vital role in facilitating a firm’s emergence from bankruptcy. The results also demonstrate financial distress risk is less seen among companies with more institutional owners that disclose more CSR information. In other words, since the goals related to CSR are long-term and Iranian institutional investors have a long-term horizon towards the company, the presence of more institutional owners within a firm push managers to provide additional voluntary CSR disclosure so firms can maintain the trust of their shareholders at the highest possible level and prevent financial distress. Our additional analysis indicates there is a positive association between financial leverage and firm failure, whereas the current ratio and ROA are negatively connected with corporate bankruptcy. Finally, when FDR is assessed on the Altman Z-score model, our evidence supports a negative relation between purchase and sale-related party transactions and bankruptcy risk, which is consistent with the efficient transaction hypothesis.

show abstract

“…Additionally, the literature review shows that in the field of public sector building energy, authors have dealt with modelling energy consumption, energy consumption by individual energy source, energy costs, and energy intensity. Methods such as support vector machine [16], decision trees [16], [46], Stochastic Impacts by Regression on Population, Affluence, and Technology (STIRPAT) [37], ridge regression [37], partition trees [49], CART [51], random forest [49], [51], and linear regression [24], [49], [50] were used. Neural network was also commonly used, as in [16], [38], [1], [48], [43], [9], [49], and [50].…”

Section: Previous Researchmentioning

confidence: 99%

“…Methods such as support vector machine [16], decision trees [16], [46], Stochastic Impacts by Regression on Population, Affluence, and Technology (STIRPAT) [37], ridge regression [37], partition trees [49], CART [51], random forest [49], [51], and linear regression [24], [49], [50] were used. Neural network was also commonly used, as in [16], [38], [1], [48], [43], [9], [49], and [50]. The methods were performed on the whole sample or on a sample divided into clusters, as in [38] and [22].…”

Section: Previous Researchmentioning

confidence: 99%

The independent component analysis with the linear regression – predicting the energy costs of the public sector buildings in Croatia

Mokriš

2022

Croat. oper. res. rev. (Online)

View full text Add to dashboard Cite

In the European Union, the public sector buildings are considered significant energy consumers and are, thus, the subject of several directives that aim to ensure the renovation of existing and the construction of new buildings as nearly zero-energy buildings. Therefore, as part of the decision making, it is necessary to properly plan the renovation or construction. This research provides models for predicting the energy costs of the public sector buildings, which are dependent upon its characteristics (i. e., constructional, occupational, energy, etc.). For this purpose, a real data set of Croatian public buildings was used, which included 150 variables and 1724 observations. Since the data set consisted of a large number of variables, the motivation for the dimensionality reduction was addressed first. Then, the independent component analysis, the principal component analysis, and the factor analysis were performed as the dimensionality reduction methods for variable extraction. The results of these analyses were used as inputs for modelling the energy costs of the public sector buildings. The obtained models were compared to the model built on original variables. The obtained models show the application potential in decision making for building renovation and construction in the public sector of Croatia, whereas the best performance of prediction in terms of RMSE and SMAPE was achieved by the model that integrated the independent component analysis with the linear regression.

show abstract

Modeling the cost of energy in public sector buildings by linear regression and deep learning

Cited by 9 publications

References 19 publications

Healthcare cost prediction based on multifactorial linear regression

Healthcare cost prediction based on multifactorial linear regression

Corporate Social Responsibility Disclosure (CSRD) and Financial Distressed Risk (FDR): Does Institutional Ownership Matter?

The independent component analysis with the linear regression – predicting the energy costs of the public sector buildings in Croatia

Contact Info

Product

Resources

About