Evaluation Optimal Prediction Performance of MLMs on High-volatile Financial Market Data

Abstract

The present study evaluates the prediction performance of the multi-machine learning models (MLMs) on high-volatile financial markets data sets since 2007 to 2020. The linear and nonlinear empirical data sets are comprised on stock price returns of Karachi stock exchange (KSE) 100-Index of Pakistan and currencies exchange rates of Pakistani Rupees (PKR) against five major currencies (USD, Euro, GBP, CHF & JPY). In the present study, the support vector regression (SVR), random forest (RF), and machine learning-linear regression model (ML-LRM) are under-evaluated for comparative prediction performance. Moreover, the findings demonstrated that the SVR comparatively gives optimal prediction performance on group1. Similarly, the RF relatively gives the best prediction performance on group2. The findings of study concludes that the algorithm of RF is most appropriate for nonlinear approximation/evaluation and the algorithm of SVR is most useful for high-frequency time-series data estimation. The present study is contributed by exploring comparative enthusiastic/optimistic machine learning model on multi-nature data sets. This empirical study would be helpful for finance and machine-learning pupils, data analysts and researchers, especially for those who are deploying machine-learning approaches for financial analysis.

Artificial neural network (ANN)-based estimation of the influence of COVID-19 pandemic on dynamic and emerging financial markets

“…Most previous studies have employed the TEMs, MLMs and SNNs to examine the COVID-19 pandemic effect on emerging financial markets. But a complex multidimensional highly volatile nonlinear financial market data can be poorly predicted by conventional approaches ( HongXing et al, 2022 ; Wookjae Heo et al, 2020 ). So, to overcome this challenge, three methodological contributions were made.…”

“…However, the present study simultaneously estimates the impact of COVID-19 pandemic on the Indian currency and derivatives markets to fulfill the research lacuna. Moreover, the numerous scholars reported that the Traditional Econometric Models (TEMs), Conventional Machine Learning Models (MLMs) and Shallow Neural Networks (SNNs) approaches cannot properly investigate the complex multidimensional and high volatile nonlinear financial market data ( HongXing et al, 2022 ; Wookjae Heo et al, 2020 ). With this motivation, the present study employs a novel ANN-based approach (DNN-based multivariate regression with a backpropagation algorithm) to estimate the influence of the COVID-19 pandemic on both financial markets.…”

Forecasting relative returns for S&P 500 stocks using machine learning

“…Based on 10 years of data on four companies, the authors of Patel et al (2015) examine the overall performance of four prediction models, ANN, SVM, RF, and Naive Bayes, and find that RF outperforms the other models in terms of trend predictions. Another study (HongXing et al 2022) applies a wide range of ML models to the highly volatile Pakistan stock market using 13 years of data and concludes that RF is best suited for nonlinear approximations.…”