• Nadendla Tharun
• Dwarapu Komal Harsha
• Nadendla Sushmitha Chowdary
• Mandala Pavani
• Kosuri Veera Bhoga Vasanth Rayalu

In the realm of cybersecurity, bolstering the adaptability of force chains against implicit pitfalls is consummate. This study delves into the realm of prophetic analytics, employing advanced machine literacy ways including CatBoost, XGBoost, and mounding Classifier. using a comprehensive dataset encompassing a plethora of features similar as IsBeta, RtpStateBitfield, and AVProductStatesIdentifier, among others, the exploration aims to develop robust models able of vaticinating cyber pitfalls. By checking pointers suchlike HasDetections andWdft_IsGamer, the models strive to identify patterns reflective of implicit security breaches. Through scrupulous analysis of attributes like Firewall status andCensus_OSBuildNumber, the study seeks to give practicable perceptivity for enhancing cyber force chain security. By integrating different classifiers, this exploration trials to offer a multifaceted approach to trouble discovery, thereby fortifying the cyber structure against arising pitfalls and icing the integrity of force chain networks.

Cat Boost, Stacking Classifier, Gradient Boost( GB) and AdaBoost.

"CYBER THREAT PREDICTIVE ANALYTICS FOR IMPROVING CYBER SUPPLY CHAIN SECURITY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.g887-g901, July-2024, Available :http://www.jetir.org/papers/JETIR2407698.pdf

"CYBER THREAT PREDICTIVE ANALYTICS FOR IMPROVING CYBER SUPPLY CHAIN SECURITY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppg887-g901, July-2024, Available at : http://www.jetir.org/papers/JETIR2407698.pdf