Analyzing and Predicting Academic Behavior from Peer Pressure Indicators Using Machine Learning

Year : 2026 | Volume : 03 | 02 | Page :
    By

    Prathmesh Tiwari,

  • Shubham Tiwari,

  • Prof. Rani Singh,

  1. Research Scholar, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharastra, India
  2. Research Scholar, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharastra, India
  3. Assistant professor, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India

Abstract

The academic achievement of a student is determined by their capability, but also by the companions with whom they associate. Friends can have a positive impact on students’ motivation for school, and at times friends are distractions leading to a lack of attention on their school assignments. This particular study focuses on the number and quality of companions students associate with and to what extent that could be used as a predictor of future performance in school by utilizing computer technology. Peer pressure is an influential factor and impacts academic achievement, and therefore this study will focus on the relationship between peer pressure and academics through machine learning methods, resulting in predictive assessments for students similar to this population.

The present research gathered student data through two means: survey and record review. The research identified members of students’ social networks who significantly influence student performance. A conceptual model was developed based on the key social network factors identified in the analysis. Computer programs known as Decision Tree, Support Vector Machine (SVM), and Random Forest were utilized to explore how these factors influenced student performance. It was discovered that how peers value and treat each other influences student performance. Random Forest was determined to be the superior computer program for predicting student performance. Educators could use this study’s results to identify students who may be negatively influenced by peer pressure; thus, they might be able to intervene prior to major academic difficulties.

Although academic performance is impacted by an individual’s effort and intelligence, the social and environmental context in which students find themselves considerably influences their behavior. Peer pressure refers to the impact of peers on the individual, causing an individual to behave in accordance with a groups norms. In general, peer pressure can either facilitate or hinder academic achievement. On one hand, positive peer pressure encourages students to work hard and achieve their academic goals; whereas, negative peer pressure encourages procrastination, reduces one’s participation or engagement level in school, and increases engagement in unproductive behavior.

Through statistical analyses, this study will evaluate the degree of peer influence on a student’s academic behaviour in order to develop predictive models to identify behavioural patterns early on. Using machine learning algorithms, educators will be able to identify students who may show detrimental behaviours and proactively provide interventions that are tailored to the individual student’s needs.

Keywords: Academic Behavior Prediction,Peer Pressure Indicators,Machine Learning,Student Performance Analytics,Educational Data Mining

How to cite this article:
Prathmesh Tiwari, Shubham Tiwari, Prof. Rani Singh. Analyzing and Predicting Academic Behavior from Peer Pressure Indicators Using Machine Learning. International Journal of Education Sciences. 2026; 03(02):-.
How to cite this URL:
Prathmesh Tiwari, Shubham Tiwari, Prof. Rani Singh. Analyzing and Predicting Academic Behavior from Peer Pressure Indicators Using Machine Learning. International Journal of Education Sciences. 2026; 03(02):-. Available from: https://journals.stmjournals.com/ijes/article=2026/view=248390


References

  1. K. D’Mello and A. Graesser, “Automatic detection of learner’s affect from conversational cues,” User Modeling and User-Adapted Interaction, vol. 18, pp. 45–80, 2008.
  2. H. Winne and A. Z. Hadwin, “Study strategies, learning tactics, and self-regulation,” in Handbook of SelfRegulation of Learning and Performance, Routledge, 2013, pp. 45–65.
  3. Fredricks, P. Blumenfeld, and A. Paris, “School engagement: Potential of the concept, state of the evidence,” Review of Educational Research, vol. 74, no. 1, pp. 59–109, 2004.
  4. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Transactions on Systems, Man, and Cybernetics, Part C, vol. 40, no. 6, pp. 601–618, 2010.
  5. Baker and K. Yacef, “The state of educational data mining in 2009: A review and future visions,” Journal of Educational Data Mining, vol. 1, no. 1, pp. 3–17, 2009.
  6. J. Hanushek and L. Woessmann, The Knowledge Capital of Nations: Education and the Economics of Growth, MIT Press, 2015.
  7. Shumway and D. Stoffer, Time Series Analysis and Its Applications, 4th ed., Springer, 2017.
  8. Nigam, A. McCallum, S. Thrun, and T. Mitchell, “Text classification from labeled and unlabeled documents using EM,” Machine Learning, vol. 39, pp. 103–134, 2000.
  9. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5–32, 2001.
  10. M. Kuhn and K. Johnson, Applied Predictive Modeling, Springer, 2013
Ahead of Print Subscription Review Article
Volume 03
02
Received 30/03/2026
Accepted 30/06/2026
Published 01/07/2026
Publication Time 93 Days
1

Login


My IP

PlumX Metrics