Instagram fake profile detection using an ensemble learning method

Counterfeit accounts still pose a big problem for Instagram users. Trust is being eroded, and online security is being compromised as a result of these accounts' constant contribution to Instagram's spam, harmful information, and deceptive content problems. To find these profiles, we use a number of analytical parameters. Using machine learning is one of the main reasons for developing a model to effectively combat these false accounts. We investigate and provide a solution to the issue of Instagram's ability to identify phony accounts in this research. An F1 score of 98%, a recall of 98%, a precision of 98.3%, and an accuracy of 98.24% are all achieved by the new, perfectly accurate model that is used in the proposed research. Our method combines scale_pos_weight optimization technique with XGBoost, SMOTE with balanced classes, and GridSearchCV to fine-tune key hyperparameters of Random Forest for fine-tuning purposes, therefore achieving this goal. This paper provides state-of-the-art methods for reducing the prevalence of false accounts, which will improve the efficiency and trustworthiness of identity verification systems used online. In this study, we provide an improved hybrid system with optimization that finds trends in phony accounts over time using adaptive discovery and strong analysis and class-balancing methods. In addition to improving online identity verification systems' detection capabilities, this framework establishes a new standard for trust safeguarding via user trust and lays the groundwork for future breakthroughs in social media security.