Ensemble Learning Based Stock Market Prediction Enhanced with Sentiment Analysis

Abstract

Besides technical and fundamental analysis, machine learning and sentiment analysis obtained from non-structural news and comments have been studied extensively in financial market prediction in recent years. It is still uncertain how to combine predictions from news, sentiment scores or financial data. In this study, we provide a methodology to achieve this issue. Besides the methodology, this study differs from previous studies in terms of data coverage and used models in both sentiment analysis and prediction. Our study consists of weekly predictions by ensemble learning and feature selection methods using 683 variables for stocks traded in the Borsa Istanbul 30 index. In addition, we predicted sentiment scores from news of 18 different sectors and combined both predictions with weighted normalized returns. We used Random Forests, Extreme Gradient Boosting and Light Gradient Boosting Machines of ensemble learning methods for predictions. From the parameters such as training set length, estimation methods, variable selection methods, number of variables, and the number of models in the prediction method, we took the combination that gives the best result. For sentiment scores, tests were performed using BERT, Word2Vec, XLNet and Flair methods. Then, we extracted final sentiment scores from the news. With the proposed trade system, we combined the results obtained from these financial variables and the news sentiment scores. Final results show that we achieved a better performance than both predictions made by using sentiment scores and financial data in terms of weekly return and accuracy.

Do Large Datasets or Hybrid Integrated Models Outperform Simple Ones in Predicting Commodity Prices and Foreign Exchange Rates?

“…A wide range of valuable Internet data, particularly textual data such as news press releases, are being evaluated for forecasting purposes in various fields, thanks to the rapid expansion of the Internet and advancements in big data technologies. Consequently, researchers are actively working on improving sentiment analysis (SA) predictions and exploring the potential of SA to enhance time series forecasting performance in different markets (Bollen et al 2011;Naeem et al 2021;Deeney et al 2015;Li et al 2016;Das et al 2018;Pai and Liu 2018;Razzaq et al 2019;Bedi and Khurana 2019;Ito et al 2019Ito et al , 2020Sivri et al 2022;Seals and Price 2020;Xiang et al 2021;Guo et al 2020;Sharma et al 2020;Mukta et al 2022).…”

Intelligent control decision integrating fuzziness and randomness for automatic management of cash flow

“…In 1965 the fuzzy mathematics theory was proposed by Prof. Zadeh [1]. Methods based on fuzzy set provide useful mathematical tools which are applied in medical diagnosis [2], electronic [3], mobile robot [4], machine learning [5], etc. to deal with the problems with uncertainty information.…”