Andere Kunden interessierten sich auch für
![Evaluating the Use of Social Media for Customer Service]( "Evaluating the Use of Social Media for Customer Service")
Evaluating the Use of Social Media for Customer Service52,99 €![Social Media Games]( "Social Media Games")
Social Media Games26,99 €![Voltage Profile Improvement Using FACTS in Transmission System]( "Voltage Profile Improvement Using FACTS in Transmission System")
Voltage Profile Improvement Using FACTS in Transmission System19,99 €![Valutazione dell'uso dei social media per il servizio clienti]( "Valutazione dell'uso dei social media per il servizio clienti")
Valutazione dell'uso dei social media per il servizio clienti37,90 €![CLASSIFICATION OF THE BEHAVIOURAL PROFILE OF DRIVERS]( "CLASSIFICATION OF THE BEHAVIOURAL PROFILE OF DRIVERS")
CLASSIFICATION OF THE BEHAVIOURAL PROFILE OF DRIVERS36,99 €![Novel Techniques in Sensory Characterization and Consumer Profiling]( "Novel Techniques in Sensory Characterization and Consumer Profiling")
Novel Techniques in Sensory Characterization and Consumer Profiling93,99 €![MACHINE LEARNING ALGORITHMS FOR FIRE DETECTION]( "MACHINE LEARNING ALGORITHMS FOR FIRE DETECTION")
MACHINE LEARNING ALGORITHMS FOR FIRE DETECTION29,99 €
In today's connected world, social media has become a vital part of our daily lives. From sharing updates and connecting with friends to exchanging ideas and accessing news, these platforms offer immense value. But alongside their popularity, a concerning issue has grown the rise of fake profiles. These accounts can be used for a variety of harmful activities spamming, phishing, spreading misinformation, manipulating opinions, or even harassing others. With millions of users online, it's nearly impossible to identify these profiles manually. This is where intelligent, automated systems come into play. This project focuses on using XGBoost (Extreme Gradient Boosting) a fast and powerful machine learning algorithm that is used to detect fake social media profiles. XGBoost is well-known for handling structured data and performing better than many traditional models, thanks to its boosting technique and inbuilt regularization that helps prevent overfitting. To train the model, we used a dataset containing various features gathered from public user profiles.