Fusion of Wavelet Decomposition and N-BEATS for improved Stock Market Forecasting

Abstract

Stock market forecasting is one of the most exciting areas of time series forecasting both for the industry and academia. Stock market is a complex, non-linear and non-stationary system with many governing factors and noise. Some of these factors can be quantified and modeled, whereas some factors possess a random walk behavior making the process of forecasting challenging. Various statistical methods, machine learning, and deep learning techniques are prevalent in stock market forecasting. Recently, there has been a paradigm shift towards hybrid models, showing some promising results. In this paper, we propose a technique that combines a recently proposed deep learning architecture N-BEATS with wavelet transformation for improved forecasting of future prices of stock market indices. This work uses daily time series data from five stock market indices, namely NIFTY 50, Dow Jones Industrial Average (DJIA), Nikkei 225, BSE SENSEX, and Hang Seng Index (HSI), for the experimental studies to compare the proposed technique with some traditional deep learning techniques. The empirical findings suggest that the proposed architecture has high accuracy as compared to some traditional time series forecasting methods and can improve the forecasting of non-linear and non-stationary stock market time series.2010 MSC: 00-01, 99-00

Business Intelligence Using N-Beats And Rnn Methods End Influence On Decision Making In The Flexible Packaging Manufacturing

“…This helps in understanding market trends, predicting product demand, and responding quickly. In addition, BI also enables cost reduction by identifying areas of waste and improving efficiency in the production process [10]. With product quality analysis, companies can improve quality and reduce defects through quick corrective actions.…”

Robust empirical wavelet fuzzy cognitive map for time series forecasting

“…Multilevel discrete decomposition (MDWD) can further extract time and frequency features of a time series in multiple levels ranging from high frequencies to low frequencies. Moreover, there are other works that achieve similar multi-rate sampling purpose (Ghysels et al, 2007), and has been applied in deep models to enhance interpretability (Wang et al, 2018;Singhal et al, 2022;Lai et al, 2018).…”