Authors:
C. Gayathri, R. Vanitha, V. Sabaresan, P. Mohaideen Fathima, M. Briskilla, Arno Onnen, Ijaz Ahad

Addresses:
Department of Computer Science and Engineering, Easwari Engineering College, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering, KCG College of Technology, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering, St. Joseph's Institute of Technology, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering in Artificial Intelligence and Machine Learning, Easwari Engineering College, Chennai, Tamil Nadu, India. School of Computer Science and Information Technology, University of Edenberg, Lusaka, Zambia. Department of Information Sciences, University of Library Studies and Information Technologies, Tsarigradsko Shose, Sofia, Bulgaria. Department of Information Sciences, Duale Hochschule Baden-Württemberg, Stuttgart, Baden-Württemberg, Germany. Department of Computer Systems Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China. Department of Computer Systems Engineering, University of Engineering and Applied Sciences, Swat, Khyber Pakhtunkhwa, Pakistan.

Abstract:

This research paper proposes a robust machine learning framework for predictive behavioral analytics that must be resilient, as multiple coordinated channels operate across hyper-connected digital platforms: user actions, device signals, service interactions and engagement traces. A purpose-designed behavioral dataset of 207 anonymized platform instances is used, collected from simulated interaction logs, controlled service events and curated response records. Indicators include session continuity, activity changes, preference stability, risk alerts, response quality and recovery behavior across social, messaging, commerce, streaming and community. The data was preprocessed, features were prepared, predictive assessments were made, and visualizations and graphs were developed for the document using Python, Jupyter Notebook, Scikit-learn, NumPy, and Matplotlib. This proposed architecture puts context handling, feature refinement, predictive processing, resilience monitoring, and decision insight into a small, readable workflow. The paper explains how behavioral signals can be processed to generate reliable foresight without resorting to overly large system designs. Resilient prediction helps interpret behavior, enables early risk recognition, and improves platform response under unstable usage. The work makes a valuable practical contribution towards adaptive, transparent and recovery-oriented analytics for interconnected digital ecosystems.

Keywords: Resilient Machine Learning; Predictive Behavioral Analytics; Hyperconnected Platforms; Digital Interaction Intelligence; Adaptive User Insight; User Actions.

Received on: 06/08/2025, Revised on: 15/10/2025, Accepted on: 30/11/2025, Published on: 09/06/2026

DOI: 10.69888/FTSIS.2026.000776

FMDB Transactions on Sustainable Intelligence and Security, 2026 Vol. 1 No. 2, Pages: 142-150

• Views : 46
• Downloads : 11

Download PDF