On Stock Market Movement Prediction Via Stacking Ensemble Learning Method

Gyamerah, Samuel Asante; Ngare, Philip; Ikpe, Dennis

doi:10.1109/cifer.2019.8759062

Cited by 14 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 11 elaborates the contribution and novelty of the proposed GBM-wFE ensemble model compared with the previous studies. Researchers in [43]proposed AdaBoost and the stacking ensemble method to predict the stock price movement and achieved a Kappa of 0.5516% as the best result; however, our model achieved a Kappa of (0.99) with the NASDAQ and Kappa of (1) with the S&P 500. Furthermore, our proposed model surpasses the proposed ensemble model in [44], in which an RMSE of 0.00 and 0.04 achieved for S&P 500 and NASDAQ respectively, whereas they had an RMSE of 0.02 in the best situation.…”

Section: Gbm-wfe Approach Benchmarkingmentioning

confidence: 83%

A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)

Nabi

Saeed

Harron

2020

KJAR

View full text Add to dashboard Cite

The prediction of stock prices has become an exciting area for researchers as well as academicians due to its economic impact and potential business profits. This study proposes a novel multiclass classification ensemble learning approach for predicting stock prices based on historical data using feature engineering. The proposed approach comprises four main steps, which are pre-processing, feature selection, feature engineering, and ensemble methods. We use 11 datasets from Nasdaq and S&P 500 to ensure the accuracy of the proposed approach. Furthermore, eight feature selection algorithms are studied and implemented. More importantly, a feature engineering concept is applied to construct two new features, which are appears to be very auspicious in terms of improving classification accuracy, and this is considered the first study to use feature engineering for multiclass classification using ensemble methods. Finally, seven ensemble machine learning (ML) algorithms are used and compared to discover the ultimate collaboration prediction model. Besides, the best feature selection algorithm is proposed. This study proposes a novel multiclass classification approach called Gradient Boosting Machine with Feature Engineering (GBM-wFE) and Principal Component Analysis (PCA) as the feature selection. We find that GBM-wFE outperforms the previous studies and the overall prediction results are auspicious, as MAPE of 0.0406% is achieved, which is considered the best result compared to the available studies in the literature.

show abstract

Section: Gbm-wfe Approach Benchmarkingmentioning

confidence: 83%

A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)

Nabi

Saeed

Harron

2020

KJAR

View full text Add to dashboard Cite

show abstract

“…Stacked ensemble along with engineered features such as difference can produce good classification results for predicting stocks at 78.10% accuracy [7]. This project will also utilize some of said features as technical indicators.…”

Section: On Stock Market Movement Prediction Via Stacking Ensemble Le...mentioning

confidence: 99%

“…Academia has since, to considerable success, explored otherwise to "beat the market" using a variety of models such as ARIMA [3], ANN [4], SVM [5], LSTM [6] and GBM [7], and also challenged EMH in behavioural psychology studies such as social media sentiment analysis [8].…”

Section: Introductionmentioning

confidence: 99%

CalixBoost: A Stock Market Index Predictor using Gradient Boosting Machines Ensemble

Wei¹,

Yeo²

2022

Artificial Intelligence Trends

View full text Add to dashboard Cite

The potential of machine learning has sustained the interest of both academia and industry in stock market prediction over the past decade. This paper aims to integrate modern techniques such as Gradient Boosting Machines (GBMs) into a novel ensemble called CalixBoost which is a resource-efficient and accurate stock index predictor. Data comprising macro-economic metrics and technical financial indicators, as well as sentiment analysis of social media using a simple and fast but effective rule-based model are used in this paper. Other techniques include model tuning with Bayesian Optimization, temporal consistency analysis for invariant feature selection over random trial-and-error, feature importance and inter-feature relationships analysis using a unified game theory approach using Shapley values. Lastly, the model will be evaluated using a novel holdout method, viz. on two separate test datasets whose datapoints are collected under (i) normal economic activity and (ii) during a black swan (financial downturn). The experimental results show that our model outperforms previous methods and can achieve a good prediction performance with 84.88% accuracy, 0.0956 RMSE, 0.0573 MAE and 4.19% MAPE.

show abstract

“…Hence, stacking ensemble learning method can be considered as a "heterogeneous ensemble model". From literatures [4,13], predictive models based on stacking ensemble models are usually better than individual model. Figure 1 is the visual diagram of stacking ensemble scheme.…”

Section: Stacking Ensemble Leanermentioning

confidence: 99%

“…The classification accuracy for their prediction was about 55%. As indicated by [4], an accuracy value closer or less than 50% for a binary classification problem is as good as randomly selecting the labels. Hence, the blockchain network-based algorithm they employed was not effective in predicting the movement in the price of Bitcoin.…”

Section: Introductionmentioning

confidence: 99%

Are Bitcoins price predictable? Evidence from machine learning techniques using technical indicators

Gyamerah

2019

Preprint

Self Cite

View full text Add to dashboard Cite

The uncertainties in future Bitcoin price make it difficult to accurately predict the price of Bitcoin. Accurately predicting the price for Bitcoin is therefore important for decision-making process of investors and market players in the cryptocurrency market. Using historical data from 01/01/2012 to 16/08/2019, machine learning techniques (Generalized linear model via penalized maximum likelihood, random forest, support vector regression with linear kernel, and stacking ensemble) were used to forecast the price of Bitcoin. The prediction models employed key and high dimensional technical indicators as the predictors. The performance of these techniques were evaluated using mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R-squared). The performance metrics revealed that the stacking ensemble model with two base learner (random forest and generalized linear model via penalized maximum likelihood) and support vector regression with linear kernel as meta-learner was the optimal model for forecasting Bitcoin price.

show abstract

On Stock Market Movement Prediction Via Stacking Ensemble Learning Method

Cited by 14 publications

References 13 publications

A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)

A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)

CalixBoost: A Stock Market Index Predictor using Gradient Boosting Machines Ensemble

Are Bitcoins price predictable? Evidence from machine learning techniques using technical indicators

Contact Info

Product

Resources

About