Robust Portfolio Design and Stock Price Prediction Using an Optimized LSTM Model

Abstract

Accurate prediction of future prices of stocks is a difficult task to perform. Even more challenging is to design an optimized portfolio with weights allocated to the stocks in a way that optimizes its return and the risk. This paper presents a systematic approach towards building two types of portfolios, optimum risk, and eigen, for four critical economic sectors of India. The prices of the stocks are extracted from the web from Jan 1, 2016, to Dec 31, 2020. Sector-wise portfolios are built based on their ten most significant stocks. An LSTM model is also designed for predicting future stock prices. Six months after the construction of the portfolios, i.e., on Jul 1, 2021, the actual returns and the LSTM-predicted returns for the portfolios are computed. A comparison of the predicted and the actual returns indicate a high accuracy level of the LSTM model.

A Performance Analysis of Technical Indicators on the Indian Stock Market

“…The classical mean-variance optimization approach stands out as the most widely recognized method for optimizing portfolios (Sen & Mehtab, 2022a;Sen et al, 2021e;Sen et al, 2021g;Sen et al, 2021h;.…”

Design and Analysis of Optimized Portfolios for Selected Sectors of the Indian Stock Market

“…Several alternative methods and propositions to the classical mean-variance portfolio optimization also exist in the literature. The multiobjective optimization techniques [15], principal component analysis [16], deep learning LSTM models [17][18][19], future risk estimation methods [20], and swarm intelligence-based approaches [21][22] are some of the very popular portfolio optimization methods. Various other approaches such as the use of genetic algorithms [23], fuzzy sets [24], prospect theory [25], quantum evolutionary algorithms [26], and time series decomposition [27] for robust portfolio design are also proposed in the literature.…”

Designing Efficient Pair-Trading Strategies Using Cointegration for the Indian Stock Market

“…For efficient portfolio design, various machine learning models have been used for the precise prediction of stock prices [8][9][10]. Models built on multiobjective optimization [11], principal component analysis [12], deep learning [13][14], and reinforcement learning [15] have also found applications in portfolio optimization and pair-trading.…”