{"id":28487630,"url":"https://github.com/sofiaamihan/box-office-analyser","last_synced_at":"2026-05-01T02:32:12.387Z","repository":{"id":297317852,"uuid":"994035087","full_name":"sofiaamihan/box-office-analyser","owner":"sofiaamihan","description":"CAI2C08 Machine Learning Final Project - Movie Worldwide Gross Revenue($) Predictive Model","archived":false,"fork":false,"pushed_at":"2025-06-07T07:09:03.000Z","size":13974,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-02T08:42:54.637Z","etag":null,"topics":["catboost-model","exploratory-data-analysis","feature-engineering","machine-learning","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sofiaamihan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-01T03:53:56.000Z","updated_at":"2025-06-07T07:09:07.000Z","dependencies_parsed_at":"2025-06-05T03:46:04.705Z","dependency_job_id":"0354c139-f38e-410f-acab-ef2e6a168c94","html_url":"https://github.com/sofiaamihan/box-office-analyser","commit_stats":null,"previous_names":["sofiaamihan/box-office-analyser"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sofiaamihan/box-office-analyser","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sofiaamihan%2Fbox-office-analyser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sofiaamihan%2Fbox-office-analyser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sofiaamihan%2Fbox-office-analyser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sofiaamihan%2Fbox-office-analyser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sofiaamihan","download_url":"https://codeload.github.com/sofiaamihan/box-office-analyser/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sofiaamihan%2Fbox-office-analyser/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32483406,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["catboost-model","exploratory-data-analysis","feature-engineering","machine-learning","python"],"created_at":"2025-06-08T04:32:19.048Z","updated_at":"2026-05-01T02:32:12.382Z","avatar_url":"https://github.com/sofiaamihan.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Box Office Analyser\nDeveloped and trained based on a [Comprehensive Film Statistics Dataset](https://www.kaggle.com/datasets/alessandrolobello/the-ultimate-film-statistics-dataset-for-ml/data), this **Worldwide Gross Revenue ($) Predictive Model \nfor Movies** served as my final submission for CAI2C08 Machine Learning. With an approximately **67% Adjusted-R² Value**, my extensive analysis and training catered quite well towards the complexity, depth, and imbalance of this \ndataset. Hosted via Streamlit, my application of this model can be accessed [here](https://sofiaamihan-box-office-analyser-application-rge5mk.streamlit.app/).\n\nInclusive of my well-researched [Report Analysis](https://github.com/sofiaamihan/box-office-analyser/blob/main/data/dataset-analysis.pdf) of the dataset, I gained valuable insights into the film industry by approaching it from a more analytical and data-driven perspective through the recognition of inherent challenges and unpredictability of box office performances.\n\n![Application Image](https://github.com/sofiaamihan/box-office-analyser/blob/main/data/application.png)\n\n## Features\nThe Box Office Analyser Repository includes several key features designed to provide insights into movie performance and revenue predictions:\n- **Predictive Model**: Utilises my well-trained advanced machine learning algorithms to predict worldwide gross revenue based on various input features.\n- **Data Visualisation**: Interactive charts and graphs to visualise relationships between impactful features.\n- **Feature Importance Analysis**: Identifies which features most significantly impact revenue predictions, helping users understand the driving factors behind box office success.\n- **User-Friendly Interface**: A Streamlit-based application that enables users to input movie data and receive instant predictions and insights.\n- **Exploratory Data Analysis (EDA)**: Provides visualisations and statistics to explore the dataset, helping users identify trends and patterns in movie performance.\n\n## Comparison with Deployment Extract \n| Actual Gross Revenue ($)     | Predicted Gross Revenue ($)     | Percentage Difference (%)     |\n|------------------------------|---------------------------------|-------------------------------|\n| 17, 475, 475                 | 22, 152, 180.67                 | 26.8                          |\n| 53, 191, 101                 | 58, 329, 482.08                 | 9.6                           |\n\n## Packages\n- `pandas`: For data manipulation and analysis.\n- `numpy`: For numerical operations and handling arrays.\n- `seaborn`: For data visualisation and statistical graphics.\n- `matplotlib`: For creating static, animated, and interactive visualisations.\n- `scikit-learn`: For implementing machine learning algorithms and model evaluation.\n- `optuna`: For hyperparameter optimisation.\n- `joblib`: For saving and loading models.\n- `catboost`, `xgboost`, `lightgbm`: For gradient boosting algorithms tailored for regression tasks, all inclusive of my tree-based algorithm choices.\n\n## Setup Instructions\n```\npip install -r requirements.txt\n```\n## Running Locally\n```\nstreamlit run application.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsofiaamihan%2Fbox-office-analyser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsofiaamihan%2Fbox-office-analyser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsofiaamihan%2Fbox-office-analyser/lists"}