Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Commodities Exchange Utilizing Diverse Deep Learning Algorithm

Download125 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343337,
        author={Anitha  Julian and Akash  R and Chennakampalli Chethan Reddy and Ramyadevi  R},
        title={Commodities Exchange Utilizing Diverse Deep Learning Algorithm},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={stock exchange time series data accuracy lstm},
        doi={10.4108/eai.23-11-2023.2343337}
    }
    
  • Anitha Julian
    Akash R
    Chennakampalli Chethan Reddy
    Ramyadevi R
    Year: 2024
    Commodities Exchange Utilizing Diverse Deep Learning Algorithm
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343337
Anitha Julian1,*, Akash R2, Chennakampalli Chethan Reddy2, Ramyadevi R1
  • 1: Saveetha Engineering College, Chennai
  • 2: Full Creative, Chennai
*Contact email: cse.anithajulian@gmail.com

Abstract

The equity market constitutes a substantial arena with a profound influence on a company's financial standing, commonly known as the stock exchange, serves as a hub for disseminating the latest global business news and developments. Professionals in the field of finance and investors meticulously scrutinize its multifaceted components. Given the sheer volume of information available concerning stocks and investments, customers often find it challenging to make predictions regarding future stock market movements. To address this challenge, customers can leverage deep learning algorithms for stock valuation. This study employs a stock price ensemble model to predict forthcoming stock market events. It harnesses time series data and historical company records to train the algorithm within the stock price ensemble model, enhancing the accuracy of future predictions. Specifically, this work focuses on refining the accuracy of the Long Short-Term Memory (LSTM) algorithm and conducting an in-depth analysis of the dataset provided.