Predicting stock market trends using random forests: A sample of the Zagreb stock exchange

Manojlović, Teo; Štajduhar, Ivan

doi:10.1109/mipro.2015.7160456

Cited by 31 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2.1). Another commonly used measure for prediction performance is the percent correctly classi¯ed (PCC) as in studies by Kumar et al (2006), Kim (2003) and Manojlovic et al (2015). The PCC is computed using equation as depicted in Eq.…”

Section: Prediction Model Evaluationmentioning

confidence: 99%

The Efficiency of Ensemble Classifiers in Predicting the Johannesburg Stock Exchange All-Share Index Direction

Mokoaleli-Mokoteli

Ramsumar

Vadapalli

2019

J. Fin. Mngt. Mar. Inst.

View full text Add to dashboard Cite

The success of investors in obtaining huge financial rewards from the stock market depends on their ability to predict the direction of the stock market index. The purpose of this study is to evaluate the efficacy of several ensemble prediction models (Boosted, RUS-Boosted, Subspace Disc, Bagged, and Subspace KNN) in predicting the daily direction of the Johannesburg Stock Exchange (JSE) All-Share index compared to other commonly used machine learning techniques including support vector machines (SVM), logistic regression and [Formula: see text]-nearest neighbor (KNN). The findings in this study show that, among all ensemble models, Boosted algorithm is the best performer followed by RUS-Boosted. When compared to the other techniques, ensemble technique (represented by Boosted) outperformed these techniques, followed by KNN, logistic regression and SVM, respectively. These findings suggest that investors should include ensemble models among the index prediction models if they want to make huge profits in the stock markets. However, not all investors can benefit from this as models may suffer from alpha decay as more and more investors use them, implying that the successful algorithms have limited shelf life.

show abstract

Section: Prediction Model Evaluationmentioning

confidence: 99%

The Efficiency of Ensemble Classifiers in Predicting the Johannesburg Stock Exchange All-Share Index Direction

Mokoaleli-Mokoteli

Ramsumar

Vadapalli

2019

J. Fin. Mngt. Mar. Inst.

View full text Add to dashboard Cite

show abstract

“…They suggested that using Lexicon based approach can increase the accuracy of the algorithm. In the research paper named Predicting stock market trends using random forests [3]T.Manojlovic and I. Stajduhar used the Random forest algorithm for the Stock Price prediction ,in results it is concluded that the prediction efficiency of algorithm is 60%.They suggested that for future research using Hybrid Model can increase the accuracy of the algorithm. In the research paper named Stock price prediction using regression based sentiment analysis [4]Yahya Eru Cakra and Bayu Distiawan Trisedya used the Linear Regression for the Stock Price prediction ,in results it is shown that the prediction efficiency of algorithm is 86.12.They suggested that Can improve accuracy using POS tagging and word weighting can increase the accuracy of the algorithm.…”

Section: Literature Surveymentioning

confidence: 99%

Fair Price based Expert System for Groceries

Syed¹

2019

IJRASET

View full text Add to dashboard Cite

E-commerce is one of the extremely fast-paced marketing businesses around the world. Over the last few decades, several major e-commerce organizations have emerged such as Amazon, Flipkart that sell the majority varieties of merchandise and also other competitors like Dollar shave club and big basket are playing a major role in this highly competitive business with domesticated products. Advantage of the use of this e-commerce manner of marketing may be available in any respect time consistent with the benefit of the customer which can also be the motive of gaining some profit within the marketplace. However, for almost, all merchandise/products charges vary. E-Commerce is a method to make the buying experience for clients extra smooth and interactive with the aid of introducing bargaining features, which are otherwise handiest familiar in physical brick and mortar stores. This can also be designed in a way that could provide gains for retailers to attract the majority of the attention and also all offers made by retailers need to have a specific goal to be reached to sell. Through this Fair-Price Model, Customers get benefited with the aid of buying the product at its quality possible price.

show abstract

“…[23] have showcased that a simple artificial neural network (76%) had a better accuracy over an SVM kernel (72%). Logistic regression, K-nearest neighbors [37], random forests [28] have also been some of the traditional machine learning algorithms investigated by the researchers but the results have not been promising.…”

Section: Introductionmentioning

confidence: 99%

A stock market trading framework based on deep learning architectures

Shah

Gor²,

Sagar³

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

Market prediction has been a key interest for professionals around the world. Numerous modern technologies have been applied in addition to statistical models over the years. Among the modern technologies, machine learning and in general artificial intelligence have been at the core of numerous market prediction models. Deep learning techniques in particular have been successful in modeling the market movements. It is seen that automatic feature extraction models and time series forecasting techniques have been investigated separately however a stacked framework with a variety of inputs is not explored in detail. In the present article, we suggest a framework based on a convolutional neural network (CNN) paired with long-short term memory (LSTM) to predict the closing price of the Nifty 50 stock market index. A CNN-LSTM framework extracts features from a rich feature set and applies time series modeling with a look-up period of 20 trading days to predict the movement of the next day. Feature sets include raw price data of target index as well as foreign indices, technical indicators, currency exchange rates, commodities price data which are all chosen by similarities and well-known trade setups across the industry. The model is able to capture the information based on these features to predict the target variable i.e. closing price with a mean absolute percentage error of 2.54% across 10 years of data. The suggested framework shows a huge improvement on return than the traditional buy and hold method.

show abstract

Predicting stock market trends using random forests: A sample of the Zagreb stock exchange

Cited by 31 publications

References 11 publications

The Efficiency of Ensemble Classifiers in Predicting the Johannesburg Stock Exchange All-Share Index Direction

The Efficiency of Ensemble Classifiers in Predicting the Johannesburg Stock Exchange All-Share Index Direction

Fair Price based Expert System for Groceries

A stock market trading framework based on deep learning architectures

Contact Info

Product

Resources

About