Decision Fusion for Stock Market Prediction: A Systematic Review

Zhang, Cheng; Sjarif, Nilam Nur Amir; Ibrahim, Roslina

doi:10.1109/access.2022.3195942

Cited by 14 publications

(4 citation statements)

References 99 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of these processing-level categories of fusion, decision fusion is aimed at learning to combine the beliefs of the collection of models into a single consensus belief [18]. Alternatively, one might say that decision fusion integrates the "decisions" of several base-learners into a single "decision" about a target [19]. This approach to "combining the wisdom of crowds" is also sometimes termed ensemble learning [20] and, in some studies, has been called "fusion models" [21], [22].…”

Section: Model Learningmentioning

confidence: 99%

“…In the taxonomy for decision-fusion combiners by Zhang, Sjarif, and Ibrahim [19], we note that algorithms can be grouped into two distinct groups. The first group are those methods that use a simple aggregation scheme for combination.…”

Section: Model Learningmentioning

confidence: 99%

“…If the base-learners come from different hypothesis classes (e.g. neural network and support vector machine), we would refer to them as heterogeneous [19].…”

Section: Model Learningmentioning

confidence: 99%

See 2 more Smart Citations

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Zyl¹

2023

Preprint

View full text Add to dashboard Cite

Meta-learning, decision fusion, hybrid models, and representation learning are topics of investigation with significant traction in time-series forecasting research. Of these two specific areas have shown state-of-the-art results in forecasting: hybrid meta-learning models such as Exponential Smoothing -Recurrent Neural Network (ES-RNN) and Neural Basis Expansion Analysis (N-BEATS) and feature-based stacking ensembles such as Feature-based FORecast Model Averaging (FFORMA). However, a unified taxonomy for model fusion and an empirical comparison of these hybrid and feature-based stacking ensemble approaches is still missing. This study presents a unified taxonomy encompassing these topic areas. Furthermore, the study empirically evaluates several model fusion approaches and a novel combination of hybrid and feature stacking algorithms called Deep-learning FORecast Model Averaging (DeFORMA). The taxonomy contextualises the considered methods. Furthermore, the empirical analysis of the results shows that the proposed model, DeFORMA, can achieve state-of-the-art results in the M4 data set. DeFORMA, increases the mean Overall Weighted Average (OWA) in the daily, weekly and yearly subsets with competitive results in the hourly, monthly and quarterly subsets. The taxonomy and empirical results lead us to argue that significant progress is still to be made by continuing to explore the intersection of these research areas.

show abstract

Section: Model Learningmentioning

confidence: 99%

Section: Model Learningmentioning

confidence: 99%

See 1 more Smart Citation

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Zyl¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Given the dynamic, non-stationary and nonlinear characteristics of financial market data, attaining dependable results proves challenging with a singular machine learning or deep learning approach for forecasting. Research has stated that these disadvantages can be overcome with a hybrid forecasting model, as opposed to the basic forecasting model, in which a single machine learning or deep learning method is used for stock forecasting ( Cui et al, 2023 ; Lv et al, 2022 ; Chopra & Sharma, 2021 ; Kanwal et al, 2022 ; Zhang, Sjarif & Ibrahim, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Multi level perspectives in stock price forecasting: ICE2DE-MDL

Akşehir,

Kılıç

2024

PeerJ Computer Science

View full text Add to dashboard Cite

This study proposes a novel hybrid model, called ICE2DE-MDL, integrating secondary decomposition, entropy, machine and deep learning methods to predict a stock closing price. In this context, first of all, the noise contained in the financial time series was eliminated. A denoising method, which utilizes entropy and the two-level ICEEMDAN methodology, is suggested to achieve this. Subsequently, we applied many deep learning and machine learning methods, including long-short term memory (LSTM), LSTM-BN, gated recurrent unit (GRU), and SVR, to the IMFs obtained from the decomposition, classifying them as noiseless. Afterward, the best training method was determined for each IMF. Finally, the proposed model’s forecast was obtained by hierarchically combining the prediction results of each IMF. The ICE2DE-MDL model was applied to eight stock market indices and three stock data sets, and the next day’s closing price of these stock items was predicted. The results indicate that RMSE values ranged from 0.031 to 0.244, MAE values ranged from 0.026 to 0.144, MAPE values ranged from 0.128 to 0.594, and R-squared values ranged from 0.905 to 0.998 for stock indices and stock forecasts. Furthermore, comparisons were made with various hybrid models proposed within the scope of stock forecasting to evaluate the performance of the ICE2DE-MDL model. Upon comparison, The ICE2DE-MDL model demonstrated superior performance relative to existing models in the literature for both forecasting stock market indices and individual stocks. Additionally, to our knowledge, this study is the first to effectively eliminate noise in stock item data using the concepts of entropy and ICEEMDAN. It is also the second study to apply ICEEMDAN to a financial time series prediction problem.

show abstract

Stock Price Prediction Through Multifaceted Data Integration and Machine Learning

Thirumalaisamy,

Ramasamy,

Abouraia

2024

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

Decision Fusion for Stock Market Prediction: A Systematic Review

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 14 publications

References 99 publications

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Multi level perspectives in stock price forecasting: ICE2DE-MDL

Stock Price Prediction Through Multifaceted Data Integration and Machine Learning

Contact Info

Product

Resources

About