A Portfolio Optimization Model for Return Trend Rate and Risk Trend Rate Based on Machine Learning - Research Report

Aug 4, 2026

Upload by Miles

A machine learning-based portfolio optimization model is presented together with a trading strategy algorithm. The method uses a long short-term memory (LSTM) network to predict stock closing prices for the next four days, then derives a return trend rate from the average rise/fall rate. A parallel process predicts the industry index’s rise/fall to form a risk trend rate. An improved mean–variance (IMV) model uses both trend rates to generate portfolio purchase decisions. Experiments on Shanghai and Shenzhen exchanges show higher annual returns and Sharpe ratio than the traditional baseline, with about 1% prediction-accuracy improvement.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Prediction-based portfolio optimization

Forecasting with stock-return prediction

Combining risk measures with portfolio optimization

A portfolio optimization model for return trend rate and risk trend rate based on machine learning Chunman Zhu1,2, Ahmad Yahya Dawod1, Yu Xi1,3, Gongsuo Chen1,2 1International College of Digital Innovation, Chiang Mai University, Chiang Mai, Thailand 2School of Information and Engineering, Sichuan Tourism University, Chengdu, China 3Office of International Collaboration and Exchange, Chengdu University, Chengdu, China Article Info ABSTRACT Article history: Received Apr 7, 2024 Revised Oct 27, 2024 Accepted Nov 14, 2024 Keywords: Long short-term memory neural network Mean–variance model Portfolio optimization Return trend rate Risk trend rate Corresponding Author: This paper presents a machine learning-based portfolio optimization model alongside a trading strategy algorithm. There are two distinct steps to the approach. Firstly, the long short-term memory (LSTM) neural network model was used to predict the closing price of stocks in the following 4 days. The average rise and fall rate over these four days is then calculated as the stock's return trend rate, which can measure the direction and intensity of the stock's rise and fall. The same method is used to predict the average of the industry index's rise and fall rate over the next four days as the risk trend rate. In the second step, the improved mean–variance model (IMV) model is used to provide customers with the stock portfolio purchasing strategy based on the return trend rate and risk trend rate. The experimental results demonstrate that the approach has a certain application value and outperforms the traditional method in terms of annual returns and Sharpe ratio, using the Shanghai Stock Exchange and the Shenzhen Stock Exchange as study samples. The model shows approximately 1% improvement in prediction accuracy. The latest advancements in machine learning provide substantial prospects for tactics involving the purchase of portfolios. This is an open access article under the CC BY-SA license. Ahmad Yahya Dawod International College of Digital Innovation, Chiang Mai University 239 Huay Kaew Rd, Suthep, Mueang Chiang Mai District, Chiang Mai-50200, Thailand Email: [ahmadyahyadawod.a@cmu.ac.th](ahmadyahyadawod.a@cmu.ac.th) 1. INTRODUCTION Portfolio management remains a prominent research field in financial investment, continuously explored by investors and researchers alike. Stock investment has the characteristics of flexible trading, significant risk-return fluctuations, modest initial capital requirements, and transparent market information, stock portfolio management is a hot research issue in securities portfolio management. In recent years, the rapid advancement of machine learning models has spurred the development and application of prediction-based portfolio optimization models in stock management. An excellent stock portfolio optimization model, with identical risk expectations, can potentially yield superior investment returns. Enhancing the performance of prediction-based stock portfolio optimization models thus holds considerable importance. Machine learning models have shown promising results in stock forecasting [1]–[5] . Markowitz introduced the mean-variance (MV) model in 1952 to address portfolio optimization, emphasizing investors'dual objectives of maximizing returns and minimizing risk. This paper divides prediction-based portfolio optimization models into two categories based on investors' decision goals. One approach to stock return forecasting assumes correctness in the forecast results and focuses solely on enhancing forecast accuracy, disregarding forecast risk. Investment portfolios are then chosen directly based on these forecasted returns [6]–[13] . Specifically, Yang Liu's comparative experiments concluded that long short-term memory (LSTM) recurrent neural networks (RNNs) perform comparably tov-type support vector regression (v-SVR) in predicting long-term volatility and outperform the generalized autoreg

FAQs

How is the return trend rate computed in this model?

The LSTM network predicts each stock’s closing price for the next four days, and the return trend rate is calculated as the average rise/fall rate over those four days to quantify direction and intensity.

What does the risk trend rate represent and how is it obtained?

The model predicts the industry index’s average rise/fall rate for the next four days using the same method, and that value becomes the risk trend rate used for portfolio construction.

How are the return trend rate and risk trend rate used to form the portfolio?

In the second step, an improved mean–variance (IMV) model determines stock portfolio purchasing strategy by balancing expected returns and risk using both trend rates.

Aug 4, 2026

Upload by Miles