TEXT ANALYTICS AND LASSO REGRESSION FOR STOCK PRICE MOVEMENTS

  • Muhammad Fikri Statistics Department, Faculty of Mathematics and Natural Sciences, Universitas Tanjungpura, Indonesia https://orcid.org/0000-0002-9490-1621
  • Shantika Martha Statistics Department, Faculty of Mathematics and Natural Sciences, Universitas Tanjungpura, Indonesia https://orcid.org/0000-0001-6124-8534
  • Evy Sulitianingsih Statistics Department, Faculty of Mathematics and Natural Sciences, Universitas Tanjungpura, Indonesia https://orcid.org/0000-0002-7133-1822
  • Wirda Andani Statistics Department, Faculty of Mathematics and Natural Sciences, Universitas Tanjungpura, Indonesia https://orcid.org/0000-0002-2210-8253
DOI: https://doi.org/10.30598/barekengvol20iss4pp2885-2900
Keywords: Event study, IDX Kompas 100, LASSO regression, Stock price movement, Text analytics, XGBoost

Abstract

This study investigates the impact of news events on stock price movements in the IDX Kompas 100 index (JKKM100) by combining machine learning-based text analytics with event study analysis using LASSO regression. News data from January 1, 2019 to July 22, 2024 were collected via web scraping and used as training data for text classification. The trained model was then applied to classify news events in the period from January 1, 2024 to April 30, 2025, which were subsequently used in the event study analysis. Stock price data for the same period (January 1, 2024 to April 30, 2025) were collected to ensure consistency between predictor and response variables. Due to class imbalance, the synthetic minority over-sampling technique (SMOTE) was applied. Several machine learning algorithms were evaluated, and XGBoost achieved the highest accuracy of 72.22%, improving to 79% after hyperparameter tuning. Using weighted abnormal returns as predictors and stock closing prices as response variables, the LASSO regression results show that 13 out of 180 news events significantly influenced stock price movements. The model explains 48.17% of the variance with an RMSE of approximately 5% of the average stock price. Industry-related news contributed the most (43.20%), followed by PESTEL (3.97%) and Investment (1.00%). This study demonstrates that integrating text analytics with LASSO-based event study provides an effective framework for analyzing the impact of news on stock price movements.

Downloads

Download data is not yet available.

References

Y. Jeon, T. H. McCurdy, and X. Zhao, “NEWS AS SOURCES OF JUMPS IN STOCK RETURNS: EVIDENCE FROM 21 MILLION NEWS ARTICLES FOR 9000 COMPANIES,” J. financ. econ., vol. 145, no. 2, pp. 1–17, 2022, doi: https://doi.org/10.1016/j.jfineco.2021.08.002.

R. Basilone, “THE IMPACT OF NEWS ON STOCK MARKET INVESTORS,” SSRN Electron. J., 2021, doi: https://doi.org/10.2139/ssrn.3908662.

A. Hussain, G. Ali, F. Akhtar, Z. H. Khand, and A. Ali, “DESIGN AND ANALYSIS OF NEWS CATEGORY PREDICTOR,” Eng. Technol. Appl. Sci. Res., vol. 10, no. 5, pp. 6380–6385, 2020, doi: https://doi.org/10.48084/etasr.3825.

G. Andani and M. L. A. Kurniawan, “ANALISIS VARIABEL MAKROEKONOMI TERHADAP INDEKS SAHAM KOMPAS 100: PENDEKATAN VECM,” J. Adv. Accounting, Econ. Manag., vol. 1, no. 3, pp. 1–17, 2024, doi: https://doi.org/10.47134/aaem.v1i3.216.

S. K. Hayumurti and K. Khomsiyah, “EVENT STUDY: CAPITAL MARKET REACTION BEFORE AND AFTER THE ANNOUNCEMENT OF PRESIDENTIAL AND VICE PRESIDENTIAL CANDIDATES 2024,” Owner, vol. 9, no. 2, pp. 1295–1303, 2025, doi: https://doi.org/10.33395/owner.v9i2.2675.

M. Freo and A. Luati, LASSO-BASED VARIABLE SELECTION METHODS IN TEXT REGRESSION: THE CASE OF SHORT TEXTS, vol. 108, no. 1. Springer Berlin Heidelberg, 2024.doi: https://doi.org/10.1007/s10182-023-00472-0

Y. Ren, F. Liao, and Y. Gong, “IMPACT OF NEWS ON THE TREND OF STOCK PRICE CHANGE: AN ANALYSIS BASED ON THE DEEP BIDIRECTIONA LSTM MODEL,” Procedia Comput. Sci., vol. 174, pp. 128–140, 2020, doi: https://doi.org/10.1016/j.procs.2020.06.068.

M. George and R. Murugesan, “IMPROVING SENTIMENT ANALYSIS OF FINANCIAL NEWS HEADLINES USING HYBRID WORD2VEC-TFIDF FEATURE EXTRACTION TECHNIQUE,” Procedia Comput. Sci., vol. 244, pp. 1–8, 2024, doi: https://doi.org/10.1016/j.procs.2024.10.172.

V. Rupapara et al., “IMPACT OF SMOTE ON IMBALANCED TEXT FEATURES FOR TOXIC COMMENTS CLASSIFICATION USING RVVC MODEL,” IEEE Access, vol. 9, pp. 78621–78634, 2021, doi: https://doi.org/10.1109/ACCESS.2021.3083638.

D. Zaria, E. Sulistianingsih, S. Martha, and W. Andani, “PERFORMANCE EVALUATION OF THE INDF.JK STOCK PRICE MOVEMENT PREDICTION MODEL USING RANDOM FOREST METHOD WITH GRID SEARCH CROSS VALIDATION OPTIMIZATION,” Barekeng, vol. 19, no. 3, pp. 2155–2168, 2025, doi: https://doi.org/10.30598/barekengvol19iss3pp2155-2168.

V. Dogra, A. Singh, S. Verma, A. Alharbi, and W. Alosaimi, “EVENT STUDY: ADVANCED MACHINE LEARNING AND STATISTICAL TECHNIQUE FOR ANALYZING SUSTAINABILITY IN BANKING STOCKS,” Mathematics, vol. 9, no. 24, pp. 1–18, 2021, doi: https://doi.org/10.3390/math9243319

E. Nurhayati, A. Hamzah, and H. Nugraha, “STOCK RETURN DETERMINANTS IN INDONESIA,” Indones. Account. J., vol. 3, no. 1, p. 45, 2021, doi: https://doi.org/10.32400/iaj.32196.

Heny Sidanti and Annisa Istikhomah, “THE EFFECT OF STOCK PRICE, SHARE RETURN, SHARE TRADING VOLUME, AND RETURN VARIANT ON BID-ASK SPREAD ON TEXTILE AND GARMENT COMPANIES LISTED ON THE INDONESIA STOCK EXCHANGE, 2019-2020,” Int. J. Sci. Technol. Manag., vol. 2, no. 4, pp. 1357–1366, 2021, doi: https://doi.org/10.46729/ijstm.v2i4.269.

M. Yunus, A. Saefudin, and A. M. Soleh, “CHARACTERISTICS OF GROUP LASSO IN HANDLING HIGH CORRELATED DATA,” Appl. Math. Sci., vol. 11, no. June, pp. 953–961, 2017, doi: https://doi.org/10.12988/ams.2017.7276.

Y. Huo, L. Xin, C. Kang, M. Wang, Q. Ma, and B. Yu, “SGL-SVM: A NOVEL METHOD FOR TUMOR CLASSIFICATION VIA SUPPORT VECTOR MACHINE WITH SPARSE GROUP LASSO,” J. Theor. Biol., vol. 486, 2020, doi: https://doi.org/10.1016/j.jtbi.2019.110098.

S. Sathyanarayanan, “CONFUSION MATRIX-BASED PERFORMANCE EVALUATION METRICS,” African J. Biomed. Res., no. December, pp. 4023–4031, 2024, doi: https://doi.org/10.53555/AJBR.v27i4S.4345.

M. Shanmugavalli and K. M. J. Ignatia, “COMPARATIVE STUDY AMONG MAPE, RMSE AND R SQUARE OVER THE TREATMENT TECHNIQUES UNDERGONE FOR PCOS INFLUENCED WOMEN M.,” Recent Patents on Engineering, vol. 19. pp. 182–189, 2025, doi: https://doi.org/10.1002/1099-0992(200009/10)30:5<613::AID-EJSP11>3.3.CO;2-J.

N. Safaeian Hamzehkolaei and M. Alizamir, “PERFORMANCE EVALUATION OF MACHINE LEARNING ALGORITHMS FOR SEISMIC RETROFIT COST ESTIMATION USING STRUCTURAL PARAMETERS,” J. Soft Comput. Civ. Eng., vol. 5, no. 3, pp. 32–57, 2021, doi: https://doi.org/10.22115/SCCE.2021.284630.1312.

C. Cristina, C. Cindy, T. Wang, D. Ng, and J. Andelson, “ANALYZING EXTERNAL ENVIRONMENT MC DONALD’S,” J. Ilmu Manaj. Profitab., vol. 8, no. 1, pp. 93–101, 2024, doi: https://doi.org/10.26618/profitability.v8i1.14031.

W. H. Lucky and T. Yuniati, “PENGARUH VARIABEL MAKRO EKONOMI TERHADAP HARGA SAHAM PADA SEKTOR PERBANKAN,” J. Ilmu dan Ris. Manaj., vol. 7, 2018, [Online]. Available: www.wikipedia.org.

W. Puspita, “PENGARUH KINERJA KEUANGAN TERHADAP HARGA SAHAM: STUDI KASUS PADA PERUSAHAAN YANG TERDAFTAR DI BEI,” Ilmu dan Ris. Akunt., vol. 6, no. 5, pp. 1941–1957, 2017.

Published
2026-08-24
How to Cite
[1]
M. Fikri, S. Martha, E. Sulitianingsih, and W. Andani, “TEXT ANALYTICS AND LASSO REGRESSION FOR STOCK PRICE MOVEMENTS”, BAREKENG: J. Math. & App., vol. 20, no. 4, pp. 2885-2900, Aug. 2026.
Issue
Vol 20 No 4 (2026): BAREKENG: Journal of Mathematics and Its Application
Section
Articles

Copyright (c) 2026 Muhammad Fikri, Shantika Martha, Evy Sulitianingsih, Wirda Andani

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this Journal agree to the following terms:

  1. Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
  2. Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
  3. Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.