Stock Prediction by Analyzing the Past Market Trend

Isha,; Dixit, Shivdutt; Ahirwar, Manoj Kumar; Sakethnath, Damam; Rakha, Manik

doi:10.1109/icrito51393.2021.9596263

Cited by 13 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the stock selection frequency of ten stocks per week, we count the returns of each research object in different intervals and judge whether it is suitable for China's A-share market according to IC and IR rankings. This paper lists the income distribution map of MACD and KDJ indicators (Figure 1 and Figure 2) [4][5][6] .…”

Section: Distribution Of Factor Incomementioning

confidence: 99%

The Validity of Quantitative Technical Indicator Factors Based on Back Testing

Zhang,

Ding,

Yang

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Technical indicator factors can quickly reflect the transformation of current market behavior. The application system in quantitative trading has become increasingly mature in recent years. Back testing is widely used in factor validity tests because of its validity. However, the current research on the effectiveness of technical indicator factors has ignored the adaptability to the model timing strategy, and the use of factors is not differentiated enough. How to carry out reasonable and effective factor validity research has become a difficult problem for many scholars to discuss. This paper first selected representative technical indicators as the research object and crawled the trading data of Chinese A-share listed companies through Python. It then calculated the sample data using computer databases such as Pandas and NumPy. Furthermore, this paper confirms the optimal interval of each factor with the method of back testing. On this basis, it tests the income distribution of each factor and the maximum pullback. It introduces the timing method of the simple moving average for comparison and discusses the feasibility of using a technical indicator strategy to conduct stock selection trading.

show abstract

Section: Distribution Of Factor Incomementioning

confidence: 99%

The Validity of Quantitative Technical Indicator Factors Based on Back Testing

Zhang,

Ding,

Yang

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

show abstract

“…In prior research conducted by us to determine the best suited model for designing the interface for stock prediction [25], it was found that ARIMA model had the best accuracy when compared with MLP and LSTM. For the research conducted a MLP model with 1987 hidden layers with the maximum iteration of 300 and three dense layers having 2200, 2570, and 2800 neurons, respectively were used [23] and similarly and LSTM model with two simple input layers with 270 and 170 neurons, another layer of 155 neurons, a dense layer of 25 neurons and an output layer of single neuron was used [25]. Also, the ARIMA model used had a moving average window of 15, lag order of 0 and degree of differencing 1 [25].…”

Section: Literature Reviewmentioning

confidence: 99%

“…For the research conducted a MLP model with 1987 hidden layers with the maximum iteration of 300 and three dense layers having 2200, 2570, and 2800 neurons, respectively were used [23] and similarly and LSTM model with two simple input layers with 270 and 170 neurons, another layer of 155 neurons, a dense layer of 25 neurons and an output layer of single neuron was used [25]. Also, the ARIMA model used had a moving average window of 15, lag order of 0 and degree of differencing 1 [25]. There have been many efforts to using various models to predict the values for various entities most of them being stocks and indices.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Designing an Interface to Forecast Stock Close Price Using ARIMA

Dixit¹,

Ahirwar²,

Saketnath³

et al. 2023

Artificial Intelligence and Communication Technologies

View full text Add to dashboard Cite

Stock market prediction involves a great effect of the current market trend on the price. It is thus necessary to create a model that efficiently identifies the market trend and predicts the values with high consistency and accuracy. This paper focuses on designing a system that uses the ARIMA model to predict the values. The python flask API has been used to design the web application and tkinter API has been used to design the GUI interface. To fetch the live market data nse2r library of R and nsetools library of python has been used to fetch the past market data for a period of six years.

show abstract

“…This paper uses various machine learning classifiers, including Decision Tree (DT), K-Nearest-Neighbour (KNN), Artificial Neural Network (ANN), Logistic Regression (LR), Random Forest (RF), AdaBoost and Support Vector Machine (Radial Basis Function). These techniques have been chosen for this study based on their straightforward implementation and efficiency in classification tasks in different fields, such as engineering [7]- [10], finance [11]- [14] and education [15]- [18].…”

Section: Introductionmentioning

confidence: 99%

Academic Performance Modelling with Machine Learning Based on Cognitive and Non-Cognitive Features

Owusu-Boadu¹,

Nti

Nyarko‐Boateng

et al. 2021

Applied Computer Systems

View full text Add to dashboard Cite

The academic performance of students is essential for academic progression at all levels of education. However, the availability of several cognitive and non-cognitive factors that influence students’ academic performance makes it challenging for academic authorities to use conventional analytical tools to extract hidden knowledge in educational data. Therefore, Educational Data Mining (EDM) requires computational techniques to simplify planning and determining students who might be at risk of failing or dropping from school due to academic performance, thus helping resolve student retention. The paper studies several cognitive and non-cognitive factors such as academic, demographic, social and behavioural and their effect on student academic performance using machine learning algorithms. Heterogenous lazy and eager machine learning classifiers, including Decision Tree (DT), K-Nearest-Neighbour (KNN), Artificial Neural Network (ANN), Logistic Regression (LR), Random Forest (RF), AdaBoost and Support Vector Machine (SVM) were adopted and training was performed based on k-fold (k = 10) and leave-one-out cross-validation. We evaluated their predictive performance using well-known evaluation metrics like Area under Curve (AUC), F-1 score, Precision, Accuracy, Kappa, Matthew’s correlation coefficient (MCC) and Recall. The study outcome shows that Student Absence Days (SAD) are the most significant predictor of students’ academic performance. In terms of prediction accuracy and AUC, the RF (Acc = 0.771, AUC = 0.903), LR (Acc = 0.779, AUC = 0.90) and ANN (Acc = 0.760, AUC = 0.895) outperformed all other algorithms (KNN (Acc = 0.638, AUC = 0.826), SVM (Acc = 0.727, AUC = 0.80), DT (Acc = 0.733, AUC = 0.876) and AdaBoost (Acc = 0.748, AUC = 0.808)), making them more suitable for predicting students’ academic performance.

show abstract

Stock Prediction by Analyzing the Past Market Trend

Cited by 13 publications

References 7 publications

The Validity of Quantitative Technical Indicator Factors Based on Back Testing

The Validity of Quantitative Technical Indicator Factors Based on Back Testing

Designing an Interface to Forecast Stock Close Price Using ARIMA

Academic Performance Modelling with Machine Learning Based on Cognitive and Non-Cognitive Features

Contact Info

Product

Resources

About