Stock Price Prediction To Support Investment Decisions

dc.contributor.authorBerboucha ,Meriem
dc.date.accessioned2026-10-13T08:07:51Z
dc.date.issued2026-06-30
dc.descriptionArticle
dc.description.abstractThis study aimed to predict stock price movements using one of the deep learning models called "Long Short-Term Memory" (LSTM), in order to support investment decisions in the financial market. In this study, the movement of stock prices of three leading technology companies "Apple Inc, Tesla Inc, and Microsoft Corp" was predicted using LSTM model. The model also generated trading signals that act as a tool to support investment decisions in the financial market. The study found that LSTM models are efficient and capable of predicting and analyzing complex patterns and time dependencies in stock prices. This confirms that LSTM recurrent neural networks are suitable for analyzing financial time series and can be considered as supporting tools to improve investment decisions
dc.identifier.citationBerboucha ,Meriem. Stock Price Prediction To Support Investment Decisions. Journal of Administrative and Financial Sciences. Vol 10. N 01. 30 June2026. faculty of economie commercial and management sciences. university of el oued .
dc.identifier.issn2602-6139
dc.identifier.urihttps://archives.univ-eloued.dz/handle/123456789/42860
dc.language.isoen
dc.publisherUniversity of Eloued جامعة الوادي
dc.subjectStock price
dc.subjectforecasting
dc.subjectRNNs
dc.subjectInvestment decisions
dc.subjectLSTM networks
dc.titleStock Price Prediction To Support Investment Decisions
dc.title.alternativeStock Price Prediction to Support Investment Decisions: A Model Based on LSTM Networks
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
stock-price-prediction-to-support-investment-decisions_-a-model-based-on-lstm-networks.pdf
Size:
642.35 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections