In the world of film industry analytics, predicting the success of movies based on various input features has garnered considerable attention in recent times. This research is important because it can help people in the movie industry make better decisions. It allows them to allocate resources effectively, minimize risks, and enhance the overall success of movie projects. This research paper presents and compares different machine learning techniques to predict the IMDb score of movies by leveraging multiple input features such as release date, genre, budget, gross revenue, profit, number of votes, country of origin, director, actor, writer, production studio, and runtime. We also account for the inflation rate over the years while considering the monetary attributes. We explore two methods: one where we transform and reduce the data using techniques like one-hot encoding and PCA, and another where we use label encoding for categorical data. In the first method, we try three models: Support Vector Regressor (SVR), RandomForest Regressor, and Recurrent Neural Network (RNN). In the second method, we use RandomForest Regressor, Gradient Boosting Regressor, and LightGBM Regressor. We measure how well these models predict by looking at Mean Squared Error (MSE) and R-squared. This research helps provide people in the film industry with insights into what factors contribute to a movie's success.