<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-05199479</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-15T12:55:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Prediction of Stock Prices Using LSTM-ARIMA Hybrid Deep Learning Model</title>
            <author role="aut">
              <persName>
                <forename type="first">Dhananjay N</forename>
                <surname>Kalange</surname>
              </persName>
              <idno type="halauthorid">3697865-0</idno>
              <affiliation ref="#struct-1458469"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Digest</forename>
                <surname>Digital</surname>
              </persName>
              <email type="md5">f248f00023a6627e0a1a024e3c5c7b0b</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-08-05 08:18:11</date>
              <date type="whenModified">2025-08-05 08:18:11</date>
              <date type="whenReleased">2025-08-05 08:18:11</date>
              <date type="whenProduced">2025-08-04</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1698517">
                <persName>
                  <forename>Digest</forename>
                  <surname>Digital</surname>
                </persName>
                <email type="md5">f248f00023a6627e0a1a024e3c5c7b0b</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05199479</idno>
            <idno type="halUri">https://hal.science/hal-05199479</idno>
            <idno type="halBibtex">kalange:hal-05199479</idno>
            <idno type="halRefHtml">&lt;i&gt;Asian Journal of Probability and Statistics&lt;/i&gt;, 2025, 27 (8), pp.28-39</idno>
            <idno type="halRef">Asian Journal of Probability and Statistics, 2025, 27 (8), pp.28-39</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Prediction of Stock Prices Using LSTM-ARIMA Hybrid Deep Learning Model</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Dhananjay N</forename>
                    <surname>Kalange</surname>
                  </persName>
                  <idno type="halauthorid">3697865-0</idno>
                  <affiliation ref="#struct-1458469"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="INCOMING">176424</idno>
                <idno type="issn">2582-0230</idno>
                <title level="j">Asian Journal of Probability and Statistics</title>
                <imprint>
                  <biblScope unit="volume">27</biblScope>
                  <biblScope unit="issue">8</biblScope>
                  <biblScope unit="pp">28-39</biblScope>
                  <date type="datePub">2025-08-04</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="math">Mathematics [math]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Aims: This study aims to develop and evaluate a hybrid LSTM-ARIMA model for predicting stock prices of major Indian commercial banks. It addresses the limitations of standalone statistical and deep learning models by combining ARIMA’s capability to model linear trends with LSTM’s strength in capturing nonlinear dependencies. Study Design: Comparative experimental design based on time-series prediction using real-world financial data. Place and Duration of Study: Data was collected for five leading Indian commercial banks—SBI, HDFC Bank, ICICI Bank, Axis Bank, and Kotak Mahindra Bank—from January 2018 to December 2023. Methodology: Daily closing prices were sourced from Yahoo Finance and NSE India. The hybrid approach first fits an ARIMA model to capture linear patterns and then applies an LSTM network to model the residuals, capturing nonlinear components. The final forecast is a summation of both model outputs. Evaluation metrics include MAE, MSE, RMSE, and MAPE. Open source software R was used for coding and the data analysis. Results: Across all five banks, the hybrid model consistently outperformed standalone ARIMA and LSTM models. For instance, in SBI, the hybrid model achieved MAPE of 2.89% compared to 4.31% (ARIMA) and 3.95% (LSTM). Similar improvements were observed for other banks, with the hybrid model maintaining MAPE below 3% and RMSE under7. Conclusion: The LSTM-ARIMA hybrid model offers a robust solution for stock price forecasting by capturing both linear and nonlinear patterns in financial time-series data. Its consistent performance across varied banks demonstrates its practical utility in financial analytics. Future research may incorporate multivariate inputs or sentiment indicators for further enhancement.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-1458469" status="INCOMING">
          <orgName>Arts, Commerce and Science College, Palus, India.</orgName>
          <desc>
            <address>
              <country key="IN"/>
            </address>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>