Related Concept Videos
Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Quantitative Analysis
In quantitative analysis, two key measurements are made: the sample quantity and a property proportional to the amount of the analyte (the substance being analyzed). This forms the basis of the...
Regression Analysis
In regression analysis, a regression equation is determined based on the line of best fit– a line that best fits the data points plotted in a graph. This line is also called the regression line. The algebraic equation for the regression line is called the regression equation. It is represented as:
Regression Toward the Mean
Improving Translational Accuracy
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Related Experiment Video
Updated: Sep 10, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
Advanced investing with deep learning for risk-aligned portfolio optimization.
1Department of Economic Information Systems, University of Economics, Hue University, Hue, Vietnam.
Deep learning models enhance portfolio optimization for diverse investor risk preferences. Long Short-Term Memory (LSTM) models outperformed 1D-CNN, leading to superior investment performance and risk-adjusted returns.
Area of Science:
- Quantitative Finance
- Computational Finance
- Machine Learning Applications
Background:
- Traditional portfolio optimization faces challenges with market volatility and diverse investor risk appetites.
- Integrating advanced predictive models is crucial for enhancing portfolio performance.
- Deep learning offers novel approaches to financial forecasting and asset allocation.
Purpose of the Study:
- To develop and evaluate a deep learning framework for portfolio optimization tailored to investor risk preferences.
- To compare the efficacy of Long Short-Term Memory (LSTM) and One-Dimensional Convolutional Neural Network (1D-CNN) in financial forecasting for portfolio construction.
- To assess the performance of different portfolio frameworks (Mean-Variance with Forecasting, Risk Parity Portfolio, Maximum Drawdown Portfolio) when integrated with deep learning predictions.
Main Methods:
- Utilized daily returns data for VN-100 stocks (2017-2024) to train and test deep learning models.
- Combined LSTM and 1D-CNN prediction models with MVF, RPP, and MDP portfolio frameworks.
- Evaluated portfolio performance based on risk-adjusted returns and total returns during the 2023-2024 test period.
Main Results:
- LSTM demonstrated superior accuracy and stability compared to 1D-CNN in forecasting stock returns.
- Portfolios constructed using LSTM predictions generally outperformed those using 1D-CNN.
- The LSTM+MVF combination yielded the best risk-adjusted returns, while LSTM+MDP achieved the highest total return.
Conclusions:
- Deep learning models, particularly LSTM, significantly improve portfolio optimization outcomes.
- Tailoring predictive models to specific portfolio frameworks enhances investment performance according to risk profiles.
- Future research should explore incorporating diverse data sources and transaction costs for more robust portfolio strategies.

