Predicting Market Performance with Hybrid Model
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
In this research, a stock market prediction model was proposed to predict performance of Karachi Stock Exchange (KSE), now merged into Pakistan Stock Exchange (PSX). The model was comprised of four sub-models that were all based on different machine learning technique. Each sub-model used 6 input attributes including fuel price, commodity, foreign exchange, interest rate, general public sentiment and related NEWS. The historical data of the market was also used for predicting the market performance using statistical techniques like Auto-Regressive Integrated Moving Average (ARIMA) and Simple Moving Average (SMA). Support Vector Machine, Radial Basis Function (RBF), Artificial Neural Network's two variants including Single Layer Perceptron and Multi-layer Perceptron were used to design four different sub-models. The results predicted by all the sub-models were merged in the Hybrid Model. The Hybrid model predicts the market performance on basis of output of each four prediction technique following the majority rule. There were two variants of Hybrid model proposed. Variant I gave about 72.8% accuracy while Variant II gave 95.7% accuracy on training data set. The Hybrid model could not predict better than the results achieved by the MLP based sub-model alone, on test data set. The results suggested that behavior of market can be predicted by using more complex model implementing different machine learning techniques.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“this study adopts three bases line ML algorithms, namely DT, SVM and NN, based on their superiority for ensemble learning in financial analysis.”
From A comprehensive evaluation of ensemble learning for stock-market prediction (2020) · cites this paper as [49]
Citations
Cites
Twitter mood predicts the stock market
Bollen, J., Mao, H., & Zeng, X. (2011) · Journal of Computational Science · doi:10.1016/j.jocs.2010.12.007 · Cited by 5,206 · cited 1×
“Similarly, few researches such as [7], showed that person’s mood plays the critical role in decision making.”
BackgroundStock market prediction using machine learning techniques
Usmani, M., Adil, S. H., Raza, K., & Ali, S. S. A. (2016) · 2016 3rd International Conference on Computer and Information Sciences (ICCOINS) · doi:10.1109/iccoins.2016.7783235 · Cited by 185
Self-citationA review of stock market prediction with Artificial neural network (ANN)
Vui, C. S., Soon, G. K., On, C. K., Alfred, R., & Anthony, P. (2013) · 2013 IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce.2013.6720012 · Cited by 108 · cited 1×
“Similarly different researches [10, 11, 12, 13] were conducted for market prediction by developing prediction models working on different techniques.”
MethodCausal relationship between macro-economic indicators and stock exchange prices in Pakistan
Ali, İ., Rehman, K. U., Yılmaz, A. K., Khan, M. A., & Afzal, H. (2010) · Global Journal of Business Management · doi:10.5897/ajbm.9000128 · Cited by 91
Performance analysis of Indian stock market index using neural network time series model
Kumar, D. A., & Murugan, S. (2013) · 2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering · doi:10.1109/icprime.2013.6496450 · Cited by 85 · cited 1×
“time series prediction for Indian Stock Market using combination of statistics and neural network [4].”
MethodExploiting Social Media for Stock Market Prediction with Factorization Machine
Chen, C., Dongxing, W., Chunyan, H., & Xiaojie, Y. (2014) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2014.91 · Cited by 34 · cited 1×
“Similarly different researches [10, 11, 12, 13] were conducted for market prediction by developing prediction models working on different techniques.”
MethodStatistical models of KSE100 index using hybrid financial systems
Fatima, S., & Hussain, G. (2008) · Neurocomputing · doi:10.1016/j.neucom.2007.11.044 · Cited by 31 · cited 1×
“In [5], the researchers have used Artificial Neural Networks (ANN) and”
MethodYu, H., & Liu, H. (2012) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2012.138 · Cited by 30 · cited 1×
“Similarly different researches [10, 11, 12, 13] were conducted for market prediction by developing prediction models working on different techniques.”
MethodProfitability of Applying Simple Moving Average Trading Rules for the Vietnamese Stock Market
Nguyen, H. H. (2013) · Journal of Business & Management · doi:10.12735/jbm.v2i3p22 · Cited by 18 · cited 1×
“In [9], researchers worked on Vietnamese Stock Market to predict the performance using variable moving average (VMA).”
MethodStock market prediction based on interrelated time series data
Kato, R., & Nagao, T. (2012) · IEEE Symposium on Computers & Informatics (ISCI) · doi:10.1109/isci.2012.6222660 · Cited by 13 · cited 1×
“Similarly different researches [10, 11, 12, 13] were conducted for market prediction by developing prediction models working on different techniques.”
Method
Research works printed but not linked: 2
- aurangzeb, 2012, Factors Affecting Performance of Stock Market: Evidence from South Asian Countries, International Journal of Academic Research in Business and Social Sciences, 2, 1
- shen, 2012, Stock Market Forecasting Using Machine Learning Algorithms
Cited by
A comprehensive evaluation of ensemble learning for stock-market prediction
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020) · Journal of Big Data · doi:10.1186/s40537-020-00299-5 · Cited by 329
“Like many other studies [18, 19, 21, 23, 49], this study adopts three bases line ML algorithms, namely DT, SVM and NN, based on their superiority for ensemble learning in financial analysis.”
MethodAn ensemble learning based hybrid model and framework for air pollution forecasting
Chang, Y., Abimannan, S., Chiao, H.-T., Lin, C.-Y., & Huang, Y. (2020) · Environmental Science and Pollution Research · doi:10.1007/s11356-020-09855-1 · Cited by 110
“Usmani et al. (2018) predicted the performance of Karachi Stock Exchange (KSE), using comprised model of four kinds of machine learning technique such as single layer perceptron (SLP), multilayer perceptron (MLP), radial basis function (RBF), and support vector machines (SVM), respectively.”
BackgroundMethodEfficient Stock-Market Prediction Using Ensemble Support Vector Machine
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020) · Open Computer Science · doi:10.1515/comp-2020-0199 · Cited by 109
“Usmani et al. [10, 11] proposed a hybrid machine learning algorithm based on SVM, Single Layer Perceptron (SLP),Multilayer Perceptron (MLP), RadialBasis Function (RBF) and Autoregressive Integrated Moving Average (ARIMA) for predicting the Karachi Stock Exchange (KSE) index.”
MethodExploring Machine Learning's Potential in Predicting Consumer Behavior for Captivating Marketing
Dahake, P. S., Mohare, R. V., & Somani, N. (2023) · International Conference On Smart Technologies For Smart Nation (SmartTechCon) · doi:10.1109/smarttechcon57526.2023.10391558 · Cited by 32
“Our research shows that machine learning techniques, like representation learning, may help add to and slow down tactics (Usmani et al., 2019).”
BackgroundIntelligent Models for Stock Price Prediction: A Comprehensive Review
Ansah, K., Denwar, I. W., & Appati, J. K. (2022) · Journal of Information Technology Research · doi:10.4018/jitr.298616 · Cited by 10
“Usmani, Ebrahim, Adil & Raza (2019) also predicted the performance of the Karachi Stock Exchange (KSE) as merged into Pakistan Stock Exchange (PSX) with a proposed Hybrid model.”
Stock Market Prediction Using Supervised Machine Learning Algorithm
Rath, S., Kumar, B., & Nayak, A. K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-4807-6_36 · Cited by 7
Buy & Sell Trends Analysis Using Decision Trees
Vaca, C., Riofrío, D., Pérez, N., & Benítez, D. S. (2020) · IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI) · doi:10.1109/colcaci50549.2020.9247907 · Cited by 4
“Many classic machine learning techniques have successfully been applied to predict market trends, to enumerate a few, artificial neural networks (ANNs), support vector machines (SVMs), and hybrid models [5]–[7].”
BackgroundInfluentialSatyaveer, Patel, P., Chandra, H., Pal, P., & Singh, S. K. (2023) · International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) · doi:10.1109/icaect57570.2023.10118349 · Cited by 3
Design a Hybrid Framework for Air Pollution Forecasting
Lin, C.-Y., Chang, Y., Chiao, H.-T., & Abimannan, S. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914257 · Cited by 2
The development of government cash forecasting model : a case study for the Indonesian government
Iskandar, I. (2019) · UTAS Research Repository · doi:10.25959/100.00033843 · Cited by 2
Modelling Stock Prices Prediction with Long Short-Term Memory (LSTM): A Black Box Approach
Bokhare, A., Rao, M., Oliver, M. P., Rai, R., & Adesara, U. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8476-3_6 · Cited by 1
PM2.5 Prediction Using Homogenous and Heterogenous Ensemble Learning: A Comprehensive Evaluation
Medhi, S., & Gogoi, M. (2024) · Journal of Computer Science · doi:10.3844/jcssp.2024.931.954 · Cited by 1
“Usmani et al .”
Bukhari, K., Jadoon, A. K., Iqbal, M., & Arshad, A. (2023) · iRASD Journal of Economics · doi:10.52131/joe.2023.0504.0185
“Only one study on the Pakistan stock market utilized macroeconomic variables, but it used only a limited set of variables and a short data time frame (Mehak Usmani et al., 2018).”
BackgroundMonpara, P., & Thummar, N. (2025) · International Conference on Advanced Machine Learning and Data Science (AMLDS) · doi:10.1109/amlds63918.2025.11159416
“[ 15] Experimental results demonstrate the effectiveness of our hybrid approach, with the SVM-based news sentiment classifier achieving 77 percentage accuracy [1] and outperforming Naive Bayes by 88 percentage in recall for lexicon-based analysis.”
Dr. Shishma Kushwaha, D. R. S., & Dr. Sudha Swaroop, D. H. S. (2025) · Journal of Informatics Education and Research · doi:10.52783/jier.v5i3.3609
Metadata
- Authors
- Usmani, M., Ebrahim, M., Adil, S. H., & Raza, K.
- Affiliations
- Iqra University (PK)
- Venue
- 2018 3rd International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST)
- Publisher
- IEEE
- Published
- 2018-12
- Pages
- 1-4
- OpenAlex
- W2915407124
- Cited by
- 13
- References
- 11
- Citations by year
- 2025: 1 · 2024: 1 · 2023: 3 · 2022: 2 · 2020: 4 · 2019: 2
- FWCI
- 2.22
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST) (publishedVersion)
- 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, hybrid forecasting model, Karachi Stock Exchange, Pakistan Stock Exchange, support vector machine, radial basis functions, artificial neural networks, multilayer perceptron, single-layer perceptron, ARIMA, simple moving average, fuel prices, commodity prices, exchange rates, interest rates, public sentiment
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.
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
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.