Forward forecast of stock prices using LSTM neural networks with statistical analysis of published messages

Faustryjak, Damian; Jackowska-Strumiłło, Lidia; Majchrowicz, Michał

doi:10.1109/iiphdw.2018.8388375

Cited by 8 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A series of tests with the suggested model were implemented and average of the outcomes was categorised using pricing data for a range of a small number of various stocks from the Bovespa stock exchange (BoSE) where LSTM centred model presented lesser risk when linked to the other strategies. LSTM recursive neural network for closing price prediction along with the information from Google trends was used by Faustryjak et al (2018). The data was taken from GPW for a period of 12/2/2017 to 4/2/2018 and headlines from Bankicr.pl website.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Techniques for Stock Market Prediction: A Review

Sable

Goel

Chatterjee

2023

IJRITCC

View full text Add to dashboard Cite

Stock market forecasting has long been viewed as a vital real-life topic in economics world. There are many challenges in stock market prediction systems such as the Efficient Market Hypothesis (EMH), Nonlinearity, complex, diverse datasets, and parameter optimization. A stock's value on the stock market fluctuates due to many factors like previous trends of the stock, the current news, twitter feeds, any online customer feedbacks etc. In this paper, the literature is critically analysed on approaches used for stock market prediction in terms of stock datasets, features used, evaluation metrics used, statistical, machine learning and deep learning techniques along with the directions for the future. The focus of this review is on trend and value prediction for stocks. Overall, 68 research papers have been considered for review from years 1998-2023. From the review, Indian stock market datasets are found to be most frequently used datasets. Evaluation metrics used commonly are accuracy and Mean Absolute Percentage Error. ARIMA is reported as the most used frequently statistical technique for stick market prediction. Long-Short Term Memory and Support Vector Machine are the commonly used algorithms in stock market prediction. The advantages and disadvantages of frequently used evaluation metrics, machine learning, deep learning and statistical approaches are also included in this survey.

show abstract

Section: Machine Learning Techniquesmentioning

confidence: 99%

Techniques for Stock Market Prediction: A Review

Sable

Goel

Chatterjee

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…al. [31] Furthermore, insightful studies with the other kinds of ML models include Kamble [13] utilizing the Random Forest algorithm on selected indicators based on their short term and long-term impact and found that the accuracy of the model was 66.8% for buy signal for short term and 75.8% for long term. Whereas the experiments using Bayesian Networks by Tan et al [19] aiming to model financial ratios of Malaysian plantation stocks around the period of the Great Recession (2007-09) received limited success as the algorithm was completely unable to predict the crash but its accuracy to classify stocks into 'buy' and 'don't buy' improved post the period of decline to 52.94% and 60.71% in 2009 and 2010 respectively.…”

Section: Machine Learning Strategies For Good Performing Stockmentioning

confidence: 99%

Feature Learning for Stock Price Prediction Shows a Significant Role of Analyst Rating

Singh

Khushi

2021

ASI

View full text Add to dashboard Cite

Efficient Market Hypothesis states that stock prices are a reflection of all the information present in the world and generating excess returns is not possible by merely analysing trade data which is already available to all public. Yet to further the research rejecting this idea, a rigorous literature review was conducted and a set of five technical indicators and 23 fundamental indicators was identified to establish the possibility of generating excess returns on the stock market. Leveraging these data points and various classification machine learning models, trading data of the 505 equities on the US S&P500 over the past 20 years was analysed to develop a classifier effective for our cause. From any given day, we were able to predict the direction of change in price by 1% up to 10 days in the future. The predictions had an overall accuracy of 83.62% with a precision of 85% for buy signals and a recall of 100% for sell signals. Moreover, we grouped equities by their sector and repeated the experiment to see if grouping similar assets together positively effected the results but concluded that it showed no significant improvements in the performance—rejecting the idea of sector-based analysis. Also, using feature ranking we could identify an even smaller set of 6 indicators while maintaining similar accuracies as that from the original 28 features and also uncovered the importance of buy, hold and sell analyst ratings as they came out to be the top contributors in the model. Finally, to evaluate the effectiveness of the classifier in real-life situations, it was backtested on FAANG (Facebook, Amazon, Apple, Netflix & Google) equities using a modest trading strategy where it generated high returns of above 60% over the term of the testing dataset. In conclusion, our proposed methodology with the combination of purposefully picked features shows an improvement over the previous studies, and our model predicts the direction of 1% price changes on the 10th day with high confidence and with enough buffer to even build a robotic trading system.

show abstract

“…We see that from the paper [9] RNN (LSTM) models are one of the best models for extraction patterns of the input features and used to span over a long sequence. They can model problems seamlessly with multiple input variables and this adds as a great benefit in time series forecasting, where simple classic regression methods can be difficult to adapt to multiple input and multivariate forecasting problems.…”

Section: Soft Computing Techniquesmentioning

confidence: 99%

A Comparative Study and Analysis of Time Series Forecasting Techniques

Athiyarath¹,

Paul²,

Krishnaswamy³

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

Time series data abound in many realistic domains. The proper study and analysis of time series data help to make important decisions. Study of such data is very useful in many applications where there are trendy changes with time or specific seasonality as in electricity demand, cloud workload, weather and sales, cost of business products, etc. By understanding the nature of the time series and the objective of analysis, we have used different approaches to learn and extract meaningful information that can satisfy the business needs. The present paper covers and compares various forecasting algorithmic approaches and explores their limitations and usefulness for different types of time series data in different domains. Keywords Time series forecast • Deep learning • ARIMA • MVFTS • CNN • LSTM • CBLSTMThis article is part of the topical collection "Advances in Computational Approaches for Artificial Intelligence, Image Processing, IoT and Cloud Applications" guest edited by Bhanu Prakash K N and M. Shivakumar.

show abstract

Forward forecast of stock prices using LSTM neural networks with statistical analysis of published messages

Cited by 8 publications

References 15 publications

Techniques for Stock Market Prediction: A Review

Techniques for Stock Market Prediction: A Review

Feature Learning for Stock Price Prediction Shows a Significant Role of Analyst Rating

A Comparative Study and Analysis of Time Series Forecasting Techniques

Contact Info

Product

Resources

About