Portfolio optimization in stocks using mean–variance optimization and the efficient frontier

Agarwal, Shiva; Muppalaneni, Naresh Babu

doi:10.1007/s41870-022-01052-2

Cited by 16 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the fundamental ideas in finance is the Efficient-Market Hypothesis (EMH) [2], which holds that asset prices accurately represent all available information. Research on the effectiveness of BTC markets has produced mixed findings; some claim that the markets are inefficient [18], while others claim that they have become more effective over time [19]. This discrepancy drives the experiments in this work, which build a model to forecast cryptocurrency values based on past prices and traded volumes and rigorously examine it.…”

Section: Related Workmentioning

confidence: 99%

Robustness Evaluation of LSTM-based Deep Learning Models for Bitcoin Price Prediction in the Presence of Random Disturbances

Kanaparthi

2024

IJISME

View full text Add to dashboard Cite

As Deep Learning (DL) continues to be widely adopted, the growing field of study on the robustness of DL approaches in finance is gaining steam. This paper investigates the robustness of a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) intended for daily closing price predictions of Bitcoin (BTC). The research entails reproducing and adjusting an LSTM design from previous research, with an emphasis on evaluating the robustness of the network. The network is trained using data that has been disturbed by Gaussian noise to assess robustness, and the effect on predictions made outside of the sample is examined. To examine the impact of adding Gaussian noise layers and noisy dense layers on training accuracy and out-of-sample predictions, further robustness tests are conducted. The results show that the LSTM network has remarkable robustness to random disturbances in the data. Nevertheless, the Root Mean Square Error (RMSE) of the prediction increases with the addition of Gaussian noise and noisy dense layers. When random noise is present in the training data, the Autoregressive Integrated Moving Average (ARIMA) model is more vulnerable to it than the LSTM, according to the robustness of the two models. These findings highlight how robustness DL techniques are overall when compared to more conventional linear methods. However, because these models are black-box, the study highlights the significance of comprehensive testing. Although the robustness of the LSTM is impressive, it is important to understand that each network may behave differently depending on the circumstances.

show abstract

Section: Related Workmentioning

confidence: 99%

Robustness Evaluation of LSTM-based Deep Learning Models for Bitcoin Price Prediction in the Presence of Random Disturbances

Kanaparthi

2024

IJISME

View full text Add to dashboard Cite

show abstract

“…By combining assets that do not move in perfect synchronization, the overall portfolio's risk can be reduced without sacrificing potential returns. This concept is illustrated by the efficient frontier, which displays the set of portfolios that offer the highest expected returns for each level of risk or the lowest risk for each level of expected returns [9]. To find the best asset allocation, MVO takes into account the variances (or standard deviations) and expected returns of the assets.…”

Section: Modern Portfolio Theorymentioning

confidence: 99%

Analysis of the State-of-art Portfolio Theory

Ying

2024

Advances in Economics, Business and Management Research

View full text Add to dashboard Cite

Portfolio theory is a fundamental concept in investment management that aims to optimize risk and return by diversifying investments across different assets. This study explores portfolio theory, including its key concepts and methodologies, such as mean-variance optimization and alternative strategies like Risk Parity and factor-based allocation. This study highlights the importance of portfolio diversification and asset allocation in achieving optimal risk-return trade-offs. The Markowitz mean-variance optimization approach provides a foundation for constructing efficient portfolios. Alternative strategies like Risk Parity and factor-based allocation offer additional perspectives for balancing risk contributions and capturing systematic risk factors. However, the limitations of these approaches, e.g., reliance on historical data and modeling assumptions, should be considered. This study provides insights into portfolio theory, empowering investors to make informed decisions when constructing investment portfolios. By understanding the principles of diversification and asset allocation, investors can effectively manage risk and optimize returns. These results contribute to the ongoing development of investment management practices, encouraging further research and innovation in portfolio construction methodologies and risk management techniques. The research's significance lies in its practical application for individuals and institutional investors seeking to maximize their investment outcomes while effectively managing risk.

show abstract

“…The application of advanced statistical methods and technological innovations enables more precise risk assessments. Researchers have explored Bayesian methods and utilized machine learning [4][5][6][7][8][9][10][11][12][13][14][15][16][17] to enhance parameter estimations. Additionally, an increasing emphasis on behavioral finance has yielded insights into investor psychology, influencing decisions on asset allocation.…”

mentioning

confidence: 99%

Navigating Uncertainty: Enhancing Markowitz Asset Allocation Strategies through Out-of-Sample Analysis

Kanaparthi

2024

FinTech

View full text Add to dashboard Cite

This research paper explores the complicated connection between uncertainty and the Markowitz asset allocation framework, specifically investigating how mistakes in estimating parameters significantly impact the performance of strategies during out-of-sample evaluations. Drawing on relevant literature, we highlight the importance of our findings. In contrast to common assumptions, our study systematically compares these approaches with alternative allocation strategies, providing insights into their performance in both anticipated and real-world out-of-sample events. The research demonstrates that incorporating methods to address uncertainty enhances the Markowitz framework, challenging the idea that longer sample periods always lead to better outcomes. Notably, imposing a short-sale constraint proves to be a valuable strategy for improving the effectiveness of the initial portfolio. While revealing the complexities of uncertainty, our study also highlights the surprising resilience of basic asset allocation approaches, such as equally weighted allocation, which exhibit commendable performance. Methodologically, we employ a rigorous out-of-sample evaluation, emphasizing the practical implications of parameter uncertainty on asset allocation outcomes. Investors, portfolio managers, and financial practitioners can use these insights to refine their strategies, considering the dynamic nature of markets and the limitations internal to the traditional models. In conclusion, this paper goes beyond the theoretical scope to provide substantial value in enhancing real-world investment decisions.

show abstract

Portfolio optimization in stocks using mean–variance optimization and the efficient frontier

Cited by 16 publications

References 34 publications

Robustness Evaluation of LSTM-based Deep Learning Models for Bitcoin Price Prediction in the Presence of Random Disturbances

Robustness Evaluation of LSTM-based Deep Learning Models for Bitcoin Price Prediction in the Presence of Random Disturbances

Analysis of the State-of-art Portfolio Theory

Navigating Uncertainty: Enhancing Markowitz Asset Allocation Strategies through Out-of-Sample Analysis

Contact Info

Product

Resources

About