A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators

Abstract

People continuously hunt for a precise and productive strategy to control the stock exchange because the monetary trade is recognised for its unbelievably different character and unpredictability. Even a minor gain in predicting performance will be extremely profitable and significant. Our novel study implemented six boosting techniques, i.e., XGBoost, AdaBoost, Gradient Boosting, LightGBM, CatBoost, and Histogram-based Gradient Boosting, and these boosting techniques were hybridised using a stacking framework to find out the direction of the stock market. Five different stock datasets were selected from four different countries and were used for our experiment. We used two-way overfitting protection during our model building process, i.e., dynamic reduction technique and cross-validation technique. For model evaluation purposes, we used the performance metrics, i.e., accuracy, ROC curve (AUC), F-score, precision, and recall. The aim of our study was to propose and select a predictive model whose training and testing accuracy difference was minimal in all stocks. The findings revealed that the meta-classifier Meta-LightGBM had training and testing accuracy differences that were very low among all stocks. As a result, a proper model selection might allow investors the freedom to invest in a certain stock in order to successfully control risk and create short-term, sustainable profits.

Robust and Secure Data Transmission Using Artificial Intelligence Techniques in Ad-Hoc Networks

“…To know the percentage enhancement against existing work, the percentage decrease was calculated. × 100 = 54.02% from [ 40 ] and × 100= 14.29% against [ 13 ] improvement in the proposed work was obtained.…”

“…SVM is a supervised machine learning model known for its excellent performance in completing classification tasks with high-dimensional data [ 37 , 38 , 39 , 40 , 41 ]. Reference [ 13 ] stated that SVM is a better choice for the detection of a malicious node in the IDS system with high accuracy and minimum error.…”

“…The studied performance was compared to prior work presented by Ali Zardariet al [ 40 ] and Gupta et al [ 13 ] to prove the efficiency of the constructed secure MANET against BHA utilizing the offered hybrid classification technique. The proposed work’s average PDR, throughput (Kbps), and delay (ms) were compared to the average PDR, throughput, and delay of existing works, as shown in Table 8 .…”

“…The comparison of PDR against the existing work performed by [ 13 , 40 ] is depicted in Table 7 . There is an improvement of 1.29% and 3.21%, respectively, against the work in [ 13 , 34 ].…”

A Hybrid Data Analytics Framework with Sentiment Convergence and Multi-Feature Fusion for Stock Trend Prediction

“…The extant research on stock trend prediction has largely focused on the application of various econometric-based methods to predict stock trends based on structured and linear historical data, mainly using linear regression and parameter estimation techniques [4][5][6][7].…”