Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 61 of the 64 references it cites were found in a registry or an index; 6 of the 55 sources its claims cite were checked for support.

A comprehensive evaluation of ensemble learning for stock-market prediction

Open access

Abstract

Abstract 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.

Overview

CoChat Summary

TL;DR

This paper compares bagging, boosting, stacking, blending, and max voting ensembles built from decision trees, SVM, and MLP for stock-market classification and regression across four exchanges. It reports that stacking and blending achieve the highest accuracy and lowest error, though at higher computational cost.

Key findings

  • Stacking and blending offered higher prediction accuracies: stacking 90–100%, blending 85.7–100%, compared with bagging 53–97.78% and boosting 52.7–96.32%; RMSE was stacking 0.0001–0.001, blending 0.002–0.01, bagging 0.01–0.11, and boosting 0.01–0.443.
  • Stacking outperformed all other combination techniques for ensemble classifiers and regressors; blending followed, then DT ensembles by boosting/bagging. DT ensemble classifiers by boosting and bagging obtained 99.98% accuracy with 10–200 estimators over GSE, BSE, and NYSE; DT boosting averaged 100% over NYSE, 95.09% over JSE, 98.52% over GSE, and 99.98% over BSE.
  • MLP bagging classifier performed better than MLP boosting: MLP bagging recorded 100% over NYSE, 81.53% over JSE, 97.98% over GSE, and 98.93% over BSE, while MLP boosting recorded 96.32% over NYSE, 62.45% over JSE, 88.99% over GSE, and 96.45% over BSE. SVM ensemble classification was low, especially on JSE (54.98% bagging; 53.02% boosting), but SVM regression had better error metrics.
  • Performance depended on dataset origin; stacking/blending were computationally expensive, while a DT ensemble of 50–100 estimators by boosting was suggested as a low-cost classifier baseline.

Methods

  • Built 25 ensemble classifiers/regressors using DT, SVM, and MLP base learners with bagging, boosting, stacking, blending, and max voting; implemented with Scikit-learn, mlens, and Python.
  • Data: market indices from GSE, JSE, NYSE, and BSE-SENSEX; the abstract says January 2012–December 2018, while Table 2 lists GSE 1100 (Jan 2012–Dec 2017, 9 features), NYSE 1760 (Jan 03 2012–Dec 2018, 15 features), JSE 1749 (Jan 2012–Dec 2018, 7 features), and BSE 984 (Jan 2015–Dec 2018, 12 features). The study predicted 30-day-ahead closing price (regression) and price movement (classification).
  • Preprocessing used wavelet transform denoising and min-max normalization; evaluation used 10-fold cross-validation, an 80/20 train/test split, and 12 accuracy/error metrics.

Limitations

  • Stated: the study predicts stock market indices, not exact stock prices; authors propose future work on feature selection and SVM parameter optimization (e.g., GA, PCA).
  • Stated: classical SVM assumes all features contribute equally and has difficulty choosing suitable parameters (C, σ, ε), affecting practicality; SVM ensemble classification was deficient with input variables and dataset sizes.
  • Evident from the text: dataset periods in Table 2 do not fully match the abstract (GSE ends Dec 2017; BSE starts Jan 2015 vs abstract Jan 2012–Dec 2018), and some table entries appear inconsistent/OCR-corrupted (e.g., MLPBotc 150 mean reported as 0.135 in the BSE table), limiting reproducibility.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s40537-020-00299-5

Cites

61 of 64 references verified2 citation errors · 1 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

5 Valid · 4 Not valid · 17 Not checked · 120 Own results and interpretations

94 more claims

Create a free account to see all 146 claims and to verify the 5 references still open.

See all claims — free account
  • It may state two separate claims as one. 28
  • Probably not a substantial claim. 19
  • Borderline: one of the tests for a substantial claim is unclear. 1
  • The quote only partly states this claim. 3

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Show all 62 references

Research works printed but not linked: 3

  1. Pimprikar R, Ramachadran S, Senthilkumar K. Use of machine learning algorithms and twitter sentiment analysis for stock market prediction. Int J Pure Appl Math. 2017;115:521–6.
  2. Priya P, Muthaiah U, Balamurugan M. Predicting yield of the crop using machine learning algorithm. Int J Eng Sci Res Technol. 2018;7:1–7.
  3. Agarwal P, Bajpai S, Pathak A, Angira R. Stock market price trend forecasting using. Int J Res Appl Sci Eng Technol. 2017;5:1673–6.

Cited by

See all 329

Metadata

Authors
Nti, I. K., Adekoya, A. F., & Weyori, B. A.
Affiliations
University of Energy and Natural Resources (GH)
Corresponding author
Nti, Isaac Kofi
Venue
Journal of Big Data
Published
2020-03-11
Volume
7
Issue
1
ISSN
2196-1115 (ISSN-L)
OpenAlex
W3013734981
Cited by
329
References
62
Citations by year
2026: 28 · 2025: 69 · 2024: 69 · 2023: 55 · 2022: 52 · 2021: 48 · 2020: 8
FWCI
25.91
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal Of Big Data (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
  • Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
Keywords
stock market prediction, ensemble learning, stacking, blending, bagging, boosting, decision tree, support vector machine, artificial neural networks, forecast accuracy comparison

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A comprehensive evaluation of ensemble learning for stock-market prediction. https://app.cochat.ai/papers/10.1186/s40537-020-00299-5
The paper
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). A comprehensive evaluation of ensemble learning for stock-market prediction. Journal of Big Data. https://doi.org/10.1186/s40537-020-00299-5

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.