Achieving accurate stock market models can provide investors with tools for making better data-based decisions. These models can help traders to reduce investment risk and select the most profitable stocks. Furthermore, creating advanced models enable the usage of non-traditional data like historical stock prices and news. There are several review articles about financial problems, including stock market analysis and forecast, currency exchange forecast, optimal portfolio selection, among others. However, the recent advances in machine learning techniques, like Deep Learning, Text Mining Techniques, and Ensemble Techniques, raises the need to perform an updated review. This study aims to fill this gap by providing an updated systematic review of the forecasting techniques used in the stock market, including their classification, characterization and comparison. The review is focused on studies on stock market movement prediction from 2014 to 2018, obtained from the scientific databases Scopus and Web of Science. Besides, it analyzes surveys and other reviews of recent studies published in the same time frame and the same databases.

Stock market movement forecast: A Systematic review

Stock-market prediction using machine-learning technique aims at developing effective and efficient models that can provide a better and higher rate of prediction accuracy. Numerous ensemble regressors and classifiers have been applied in stock market predictions, using different combination techniques. However, three precarious issues come in mind when constructing ensemble classifiers and regressors. The first concerns with the choice of base regressor or classifier technique adopted. The second concerns the combination techniques used to assemble multiple regressors or classifiers and the third concerns with the quantum of regressors or classifiers to be ensembled. Subsequently, the number of relevant studies scrutinising these previously mentioned concerns are limited. In this study, we performed an extensive comparative analysis of ensemble techniques such as boosting, bagging, blending and super learners (stacking). Using Decision Trees (DT), Support Vector Machine (SVM) and Neural Network (NN), we constructed twenty-five (25) different ensembled regressors and classifiers. We compared their execution times, accuracy, and error metrics over stock-data from Ghana Stock Exchange (GSE), Johannesburg Stock Exchange (JSE), Bombay Stock Exchange (BSE-SENSEX) and New York Stock Exchange (NYSE), from January 2012 to December 2018. The study outcome shows that stacking and blending ensemble techniques offer higher prediction accuracies (90–100%) and (85.7–100%) respectively, compared with that of bagging (53–97.78%) and boosting (52.7–96.32%). Furthermore, the root means square error (RMSE) recorded by stacking (0.0001–0.001) and blending (0.002–0.01) shows a better fit of ensemble classifiers and regressors based on these two techniques in market analyses compared with bagging (0.01–0.11) and boosting (0.01–0.443). Finally, the results undoubtedly suggest that an innovative study in the domain of stock market direction prediction ought to include ensemble techniques in their sets of algorithms.

/pdf/a-comprehensive-evaluation-of-ensemble-learning-for-stock-14pcf72a0y.pdf

A comprehensive evaluation of ensemble learning for stock-market prediction

Financial Analysis has become a challenging aspect in today’s world of valuable and better investment. This paper introduces the implementation of Recurrent Neural Network (RNN) along with Long Short-Term Memory Cells (LSTM) for Stock Market Prediction used for Portfolio Management considering the Time Series Historical Stock Data of Stocks in the Portfolio. The comparison of the model with the traditional Machine Learning Algorithms—Regression, Support Vector Machine, Random Forest, Feed Forward Neural Network and Backpropagation have been performed. Various metrics and architectures of LSTM RNN model have been considered and are tested and analysed. There is discussion on how the sentiments of the customer would affect the stocks along with the changes in trends.

Stock Market Price Prediction Using LSTM RNN

Combining multiple classifiers to create hybrid learners (ensembles) has gained popularity in recent years. Ensembles are gaining more interest in the field of data mining as they have reportedly performed best predictions as compared to individual classifiers. This has resulted in experimentation with new ways of ensemble creation. This paper presents a study on creation of novel hybrid ways of combining multiple ensemble models using ‘over production and choose approach.’ In contrast to the original concept of ensembles that combine various learners, the proposed ensemble models comprise of combinations of other ensembles. In particular, we have combined learners as in composition of other learners, thus producing nested learners. Two such models named as Boosted-Stacked learners and Bagged-Stacked learners are proposed and are shown to outperform the traditional ensembles. Experiments are performed in churn prediction domain where a benchmark customer churn dataset (available on UCI repository) and a newly created dataset from a South Asian wireless telecom operator (named as SATO) are used. SATO dataset is created as balanced dataset (having equal number of churners and non-churners). The novel Boosted-Stacked learner and Bagged-Stacked learner achieved accuracies of 98.4% and 97.2%, respectively, on the UCI Churn dataset outperforming the existing state-of-the-art techniques. Furthermore, a high accuracy on the SATO dataset validates the effectiveness of the proposed models on balanced as well as imbalanced datasets.

Exploring nested ensemble learners using overproduction and choose approach for churn prediction in telecom industry

The recent success of the application of Artificial Intelligence in the financial sector has resulted in more firms relying on stochastic models for predicting the behaviour of the market. Everyday, quantitative analysts strive to attain better accuracies from their machine learning models for forecasting returns from stocks. Support Vector Machine (SVM) and Random Forest based regression models are known for their effectiveness in accurately predicting closing prices. In this work, we propose a technique for analyzing and predicting stock prices of companies using the aforementioned algorithms as an ensemble. Datasets from India's National Stock Exchange (NSE) containing basic market price information are preprocessed to include well known leading technical indicators as features. Feature selection, which ranks features based on their degree of influence on the final closing price has been incorporated to reduce the size of the training dataset. Additionally, we evaluate the effectiveness of considering the public opinion of a company by employing sentiment analysis. Using a trained Word2Vec model, company specific hash-tagged posts from Twitter are classified as positive or negative. Our proposed ensemble model is then trained on a new dataset which combines the technical indicator data along with the aggregated number of positive/negative tweets of a company over time. Our experiments indicate that in some scenarios, the ensemble model performs better than the constituent models and is highly dependent of the nature and size of the training data. However, combining technical indicator data with aggregated positive/negative tweet counts has a negligible effect on the performance of the ensemble model.

Predicting Stock Prices using Ensemble Learning and Sentiment Analysis

Precisely predicting the stock price movement trend is essential for investors to gain enormous profit. However, due to the complicated financial environment, it is challenging to make an accurate market prediction. Machine learning is an effective tool to make such predictions. To build an effective investment strategy, selections of input features, prediction model with high accuracy, and buy-and-sell signals are very important factors. In this paper, we firstly screened out training features that are most relevant to stock price movement by calculating maximal information coefficient (MIC), then built an ensemble prediction model named SRAVoting basing on three outstanding classifiers on stock price movement trend prediction (support vector machine (SVM), random forest (RF), and AdaBoost (AB)), and proposed stock buy & sell strategies for day-span, week and month investing periods. Chinese stock price indexes and technical indicators were used to validate the proposed model and strategy. Result showed that SRAVoting model achieved higher prediction accuracy than SVM, while not necessarily higher annualized return rate than SVM based buy & sell strategies. Overall, the SRAVoting based strategies on different investing periods may benefit investors with positive returns.

Jian Yang

Papers

Ensemble Model for Stock Price Movement Trend Prediction on Different Investing Periods