Movie Predictor

• GIF

  Demo

• 

  Architecture

Inspiration

The inspiration behind our movie predictor project came from our passion for movies and the desire to explore machine learning techniques. We wanted to create a tool that could predict movie ratings based on various factors such as genre, director, and cast. Additionally, we aimed to provide personalized movie recommendations to users based on their preferences and viewing history.

What it does

Our movie predictor project utilizes machine learning algorithms to predict movie ratings and provide personalized recommendations. Users can input movie details such as genre, director, and cast, and the system will generate a predicted rating. Additionally, users can create profiles and receive tailored movie recommendations based on their previous ratings and viewing history.

How we built it

We built the movie predictor project using MongoDB Atlas for storing movie data and user profiles. We utilized Google Cloud for training and deploying our machine learning models. The project was developed using Python and popular machine learning libraries such as scikit-learn and TensorFlow. We also leveraged APIs and web frameworks to create a user-friendly interface for interacting with the system.

Challenges we ran into

During the development process, we faced several challenges. One of the main challenges was acquiring and cleaning a large dataset of movies and ratings. We had to ensure data quality and handle missing values effectively. Additionally, training accurate machine learning models and optimizing their performance posed a significant challenge. We also encountered difficulties in integrating MongoDB Atlas with our application and managing user profiles securely.

Accomplishments that we're proud of

We are proud of successfully implementing the movie predictor project and achieving accurate predictions for movie ratings. Our personalized recommendation system has been well-received by users, and we have received positive feedback on its accuracy and usefulness. Additionally, we were able to deploy the project on Google Cloud, ensuring scalability and reliability.

What we learned

Throughout the development of the movie predictor project, I learned valuable lessons. I gained hands-on experience in data preprocessing, feature engineering, and model training. We also improved our understanding of MongoDB Atlas and its integration with our application. Additionally, I learned using BigQuery data in Vertex AI AutoML integration.

What's next for Movie Predictor

In the future, I plan to enhance the movie predictor project by incorporating more advanced machine learning techniques, such as deep learning algorithms, to improve prediction accuracy. I can play around with the independent variables and try to increase the accuracy of the prediction result. I am also considering to take this process one step further and try the same problem as a Linear Regression model by predicting the score as a float/decimal point value instead of rounded integers. Additionally, I plan to optimize the performance and scalability of the system to handle a larger user base and dataset.

Built With

• 6.
• ai
• angular.js
• atlas
• automl
• bigquery
• cloud-storage
• cloudrun
• java
• mongodb
• vertex