Portfolio optimization in district heating: Merit order or mixed integer linear programming?

González-Salazar, Miguel Angel; Klossek, Julia; Dubucq, Pascal; Punde, Thomas

doi:10.1016/j.energy.2022.126277

Cited by 14 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM, through its ability to find the hyperplane that best separates different classes in the dataset, can classify assets into varying risk categories. For example, an SVM model can be trained on historical data to classify stocks into 'high', 'medium', or 'low' risk categories based on features like volatility, beta (a measure of an asset's volatility in relation to the market), and financial ratios such as the debt-to-equity ratio [3]. Decision Trees, another popular classification method, offer an intuitive and visual approach to decision-making by breaking down a dataset into smaller subsets while at the same time developing an associated decision tree.…”

Section: Classification Algorithms For Risk Assessmentmentioning

confidence: 99%

Advancing portfolio optimization: The convergence of machine learning and traditional financial models

Huang

2024

ACE

View full text Add to dashboard Cite

This paper delves into the transformative impact of machine learning (ML) on portfolio optimization, showcasing how ML algorithms can significantly enhance traditional financial models such as the Capital Asset Pricing Model (CAPM) and the Arbitrage Pricing Theory (APT). Through a comprehensive examination of regression analysis, classification algorithms, and reinforcement learning, we illustrate the methodologies by which ML refines the prediction of asset returns, assesses investment risks, and dynamically adjusts portfolio allocations. We discuss the integration of ML with CAPM and APT to improve the estimation of systematic risk and identify multi-factor influences on asset returns, offering a more nuanced approach to optimizing portfolios. Additionally, the paper highlights the role of big data in augmenting predictive accuracy and the application of optimization algorithms like Gradient Descent and Genetic Algorithms in achieving optimal asset allocations. By addressing challenges such as multicollinearity and overfitting, we demonstrate the potential of ML to revolutionize investment strategies, enabling more sophisticated risk management and return maximization. This study not only underscores the synergy between ML and traditional financial theories but also paves the way for future innovations in financial analytics.

show abstract

Section: Classification Algorithms For Risk Assessmentmentioning

confidence: 99%

Advancing portfolio optimization: The convergence of machine learning and traditional financial models

Huang

2024

ACE

View full text Add to dashboard Cite

show abstract

“…Storage technologies are still not efficient enough to remove the coupling between supply and demand in markets, but with technology development and reduction in cost, this paradigm can be changed [30], [31]. Another study [32] targets the problem of district heating by utilizing portfolio optimization in conjunction with integer based programming.…”

Section: A Literature Reviewmentioning

confidence: 99%

Diversification of Energy Resources for Electricity Generation in Pakistan via Portfolio Optimization

Shafique,

Rashid,

Awan

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The aim of this paper is to investigate Pakistan's efficient generation portfolios by comparing the portfolio costs, risks, efficient frontiers, and diversification levels under different cases and scenarios. Uncertainty in the energy sector of Pakistan has contributed to the necessity of effective electricity planning that can minimize given market risks and discourage the use of stand-alone generating costs. This paper presents a novel energy production optimization empirically using mean-variance portfolio theory. The proposed research work leverages the mean-variance portfolio theory to design an efficient electricity generation mix to diversify its energy mix by investing in renewable energy sources. The portfolio optimization for the energy sector is driven by the minimization of either the cost or risk of the energy resource portfolio subject to various budget constraints. In the context of decentralized energy sources, the current work presents an optimal portfolio design that takes into account average costs, risks, and diversity of the energy resources for electricity generation. This is followed by the computation of optimal efficient frontier for energy portfolio based on extensive statistical analysis over data collected for eight different technologies, namely coal, high-speed diesel, fuel oil, gas, solar, wind, and hydro. Numerical results reveal that diversification of energy sources, which consists of a mixture of all technologies, yields a solution that guarantees reliability of more than 90% for the given data.

show abstract

“…Basically, the topic of stock portfolio optimization is a highly researched topic with many dimensions. Many researches have been done on the general topic of stock portfolio optimization, but in terms of using the issue of liquidity in this research, it has tried to examine the history of research that includes this feature in the past few decades [9].…”

Section: Literature Reviewmentioning

confidence: 99%

Presenting a combined econometric model to optimize the stock portfolio in the stock exchange

Hajiaghajani

2023

IJIMES

View full text Add to dashboard Cite

Purpose: Portfolio optimization is one of the important issues in the field of financial sciences and investment, which has many applications in financial planners and decisions. By choosing a suitable stock portfolio, it is possible to greatly increase the efficiency of investment (in terms of increasing returns and reducing risk). Methodology: In this paper, by presenting a model of liquidity risk, using the concept of diversification in the form of Shannon's entropy and econometric approach, an optimal portfolio of investment with the lowest risk and the highest return has been presented in the form of a portfolio. To calculate the liquidity risk, using multivariable methods, the variance-covariance matrix of price index returns and price gap was calculated and used in the presented model, and finally, the optimal weight was used using the optimization method and meta-heuristic algorithm of non-dominant ranking of the second version., calculated for selected industries. Findings: The output results of the model show that the optimal weight of the groups that have less variance in the optimal portfolio is higher. Originality/Value: Besides, the effect of removing the concept of liquidity from the model leads to an increase in the weight of industries that have less liquidity, and along with the increase in risk, the return of the optimal portfolio also increases in this case.

show abstract

Portfolio optimization in district heating: Merit order or mixed integer linear programming?

Cited by 14 publications

References 47 publications

Advancing portfolio optimization: The convergence of machine learning and traditional financial models

Advancing portfolio optimization: The convergence of machine learning and traditional financial models

Diversification of Energy Resources for Electricity Generation in Pakistan via Portfolio Optimization

Presenting a combined econometric model to optimize the stock portfolio in the stock exchange

Contact Info

Product

Resources

About