Dynamic portfolio optimization using technical analysis‐based clustering

Abstract

An accurate prediction of asset prices is perhaps the biggest challenge of any study in portfolio optimization.Asset prices are affected by several random and nonrandom factors, which makes them difficult to forecast. This paper proposes a two-phase dynamic portfolio optimization approach. In the first phase, assets are clustered into buy, sell, and hold groups using technical indicators. We provide a methodology to integrate the investor attitude (optimistic, pessimistic, or neutral) during the clustering phase. In the second phase, we input the clustered groups into a portfolio optimization model to obtain the optimum asset allocations. We use coherent fuzzy numbers to model the asset returns to integrate the investor attitude in this phase. The optimization model is solved using a genetic algorithm. The portfolios are rebalanced at regular intervals as new data becomes available. We illustrate the proposed methodology on a 100-asset problem of the US stock market. We analyze the real-world performance of the obtained portfolios. We compare the performance of the proposed approach with the mean-variance model, and other portfolios, such as the naïve portfolio and the NASDAQ-100 index.

Dynamic Portfolio Rebalancing with Lag-Optimised Trading Indicators Using Serofam and Genetic Algorithms

“…Technical analyses are commonly performed by AMFs and investors, which aim to predict future market or price trends with historical market data or trading information by technical indicators (Hoseinzade & Haratizadeh, 2019;Khan & Mehlawat, 2022). Market trends are the tendency of financial markets moving to certain direction within particular timeframes, that can affect investment behaviours (Alhnaity & Abbod, 2020;Fontanills & Gentile, 2001;Ngoc, 2014).…”

“…The asset re-allocations are conducted based on risk taking attitudes of investors and several technical indicators, such as moving average, Stochastics oscillator, etc. (Khan & Mehlawat, 2022). A support vector machine (SVM) recursive feature elimination method is presented to predict one-day ahead movement using RSI and two other technical indicators (Weng, Ahmed, & Megahed, 2017).…”

Mechanisms of Stock Selection and Its Capital Weighing in the Portfolio Design Based on the MACD-K-Means-Mean-VaR Model

“…Chen et al [13] and Cheong et al [14] employed the K-means technique to cluster stock data based on the average return attribute. Khan and Mehlawat [15] employed fuzzy C-means clustering to group stocks into clusters. Then, Sáenz [16] investigated the application of clustering models for stocks to enhance the accuracy of stock price predictions and the performance of trading algorithms.…”

Portfolio Optimization Strategy Based on Risk Diffusion Model in Emerging Industry Development

“…The optimal strategy values are also derived by developing new algorithms and discussing, in-depth, the effects of preset terminal targets, input delay lengths and risk jump intensities on optimal investments. Literature [21] proposes a two-stage dynamic portfolio optimization approach to obtain the optimal asset allocation in order to accurately predict the price of the investment assets, modeling the asset returns through coherent fuzzy numbers. The optimization model is solved through the integration of investor attitudes using the genetic algorithm.…”