Machine Learning Projects

  Movie Recommendation System Using TF-IDF Vectorizer: Enhancing Personalization through Content-Based Filtering Abstract In the realm of digital entertainment, personalized movie recommendations play a crucial role in enhancing user experience and engagement. This study presents a movie recommendation system that employs the TF-IDF (Term Frequency-Inverse Document Frequency) Vectorizer to analyze and recommend movies based on their content. By transforming movie descriptions into numerical vectors, the system identifies similarities between movies and generates recommendations tailored to user preferences. The effectiveness of the system is evaluated through various metrics, demonstrating its capability to provide relevant movie suggestions and improve user satisfaction. Introduction Movie recommendation systems are essential tools for managing the vast array of content available in digital platforms. Traditional methods, such as collaborative filtering, rely on user inter...

  Spam Mail Prediction Using Logistic Regression: Enhancing Accuracy in Email Filtering Systems Abstract Spam mail detection is a crucial task in email management systems, aimed at filtering unwanted and potentially harmful messages. In this study, we applied Logistic Regression to predict spam emails from a dataset containing various features derived from email content. The model achieved high accuracy scores of 96.70% on training data and 96.59% on test data, demonstrating its effectiveness in distinguishing between spam and non-spam emails. The results underscore the robustness of Logistic Regression in handling binary classification problems in natural language processing applications. Introduction Spam mail, or unsolicited and often malicious email, poses significant challenges to users and email service providers. Effective spam detection is essential for improving user experience and safeguarding against potential threats. Logistic Regression, a widely used classific...

Calories Burnt Prediction Using XGBoost Regressor: Enhancing Accuracy with Gradient Boosting Techniques Abstract Accurately predicting the number of calories burnt based on various input features is critical for personalized health and fitness applications. In this study, we apply the XGBoost Regressor, a powerful gradient boosting algorithm, to predict calories burnt from activity data. The model was trained and evaluated on a dataset comprising features such as activity type, duration, and intensity. The XGBoost model achieved a Mean Absolute Error (MAE) of 2.72, indicating a strong performance in predicting calories burnt with minimal deviation from actual values. This study demonstrates the effectiveness of gradient boosting techniques in the domain of health and fitness prediction. Introduction With the increasing focus on health and fitness, accurate prediction of calories burnt during physical activities is of paramount importance. Various models and methods have been ex...

Titanic Survival Prediction Using Logistic Regression: A Data-Driven Approach to Understand Survival Factors Abstract The Titanic disaster remains one of the most infamous maritime tragedies, and its dataset provides a valuable opportunity to study the factors influencing survival rates using data analysis. In this study, we employ Logistic Regression, a widely-used statistical classification algorithm, to predict the survival of passengers aboard the Titanic. Using features such as passenger class, age, gender, and other socio-economic factors, the Logistic Regression model achieved an accuracy of 78.21% on the test data. The findings suggest that gender, class, and age were significant factors affecting survival, offering insights into the predictive power of statistical modeling for classification problems. Introduction The RMS Titanic sank in the early hours of April 15, 1912, during its maiden voyage, resulting in over 1,500 deaths. Many efforts have been made to analyze the facto...

  Parkinson's Disease Detection Using Support Vector Machine: A Machine Learning Approach for Early Diagnosis Abstract Parkinson's Disease (PD) is a progressive neurological disorder that affects millions of people worldwide. Early detection of PD is crucial for providing timely treatment and improving patient quality of life. In this study, we employ a Support Vector Machine (SVM) algorithm to detect Parkinson's Disease based on biomedical voice measurements. SVM, a supervised machine learning technique, is used to classify patients as either suffering from Parkinson's or healthy. The model achieved an accuracy score of 88.46% on the training data and 87.18% on the test data. The results show that SVM is an effective tool for detecting PD, offering high accuracy and reliability. This study underscores the potential of machine learning in medical diagnostics, specifically for early detection of neurological disorders. Introduction Parkinson's Disease (PD) is...