{"id":19653825,"url":"https://github.com/serverdaun/ml_project_sber","last_synced_at":"2026-05-08T02:03:38.117Z","repository":{"id":245714746,"uuid":"789870947","full_name":"serverdaun/ml_project_sber","owner":"serverdaun","description":"This repository contains a machine learning project aimed at predicting user actions on a car subscription service’s website.","archived":false,"fork":false,"pushed_at":"2024-09-10T21:50:44.000Z","size":11271,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-10T00:22:00.661Z","etag":null,"topics":["classification-algorithm","fastapi","machine-learning","predictive-modeling","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/serverdaun.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}},"created_at":"2024-04-21T19:21:00.000Z","updated_at":"2024-09-10T21:50:48.000Z","dependencies_parsed_at":"2024-06-23T16:54:47.281Z","dependency_job_id":"84edd7ac-646b-448e-8e58-a50bc9571149","html_url":"https://github.com/serverdaun/ml_project_sber","commit_stats":null,"previous_names":["serverdaun/ml_project_sber"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/serverdaun%2Fml_project_sber","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/serverdaun%2Fml_project_sber/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/serverdaun%2Fml_project_sber/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/serverdaun%2Fml_project_sber/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/serverdaun","download_url":"https://codeload.github.com/serverdaun/ml_project_sber/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240962565,"owners_count":19885498,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["classification-algorithm","fastapi","machine-learning","predictive-modeling","python"],"created_at":"2024-11-11T15:15:22.446Z","updated_at":"2026-05-08T02:03:33.056Z","avatar_url":"https://github.com/serverdaun.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ML Project: Sber Auto Subscription\n\n## Table of Contents\n1. [Introduction](#introduction)\n2. [Project Structure](#project-structure)\n3. [Installation](#installation)\n4. [Usage](#usage)\n\n\n## Introduction\nThis project involves developing a machine learning model for a car subscription service.\nThe main task is to predict whether a user will perform a target action on the company's website.\nKey aspects of the project include:\n\n1. Working with Google Analytics data to analyze user behavior on the website.\n2. Developing a predictive model to determine if a user will perform a target action (e.g., submitting an application or requesting a call).\n3. The goal is to achieve a ROC-AUC score of approximately 0.65.\n4. Creating a service that takes input features such as UTM parameters, device information, and geo data, and outputs a binary prediction (0 or 1) indicating whether the user is likely to perform a target action.\n5. The project requires data preprocessing, feature engineering, model selection, and API implementation.\n\n\n## Project Structure\n- **data/skillbox_diploma_main_dataset_sberautopodpiska** # Contains two datasets: information about sessions and information about hits\n- **notebooks/** # Jupyter notebooks for data preprocessing, EDA, feature engineering, and modeling\n- **model/** # Directory for model files:\n  - **pipeline.py** # Steps for model creation\n  - **model.pkl** # Final trained model\n- **main.py** # FastAPI app configuration\n- **requirements.txt** # Python dependencies\n- **README.md** Project documentation\n\n## Installation\n1. Clone the repository\n    ```sh\n    git@github.com:serverdaun/ml_project_sber.git\n    cd ml_project_sber\n    ```\n2. Create and activate a virtual environment\n    ```sh\n    python3 -m venv venv\n    source venv/bin/activate\n    ```\n3. Install the required dependencies\n    ```sh\n    pip install -r requirements.txt\n    ```\n\n## Usage\n1. Start the FastAPI application to serve the model and make predictions through a REST API.\n   ```sh\n   uvicorn main:app --reload\n   ```\n2. Once the server is running, you can use tools like 'curl' or Postman to make requests to the API. Below is the list\nof the calls.\n- GET\n  - 'http://127.0.0.1:8000/status' to get the status of the app\n  - 'http://127.0.0.1:8000/version' to get model metadata \n- POST\n  - 'http://127.0.0.1:8000/predict' to make predictions with json format data in body\n\n3. Example data for API\n    ```sh\n   {\n    \"session_id\": \"9055434745589932991.1637753792.1637753792\",\n    \"client_id\": \"2108382700.1637753791\",\n    \"visit_date\": \"2021-11-24\",\n    \"visit_time\": \"14:36:32\",\n    \"visit_nuber\": 1,\n    \"utm_source\": \"ZpYIoDJMcFzVoPFsHGJL\",\n    \"utm_medium\": \"banner\",\n    \"utm_campaign\": \"LEoPHuyFvzoNfnzGgfcd\",\n    \"utm_adcontent\": \"vCIpmpaGBnIQhyYNkXqp\",\n    \"utm_keyword\": \"puhZPIYqKXeFPaUviSjo\",\n    \"device_category\": \"mobile\",\n    \"device_os\": \"Android\",\n    \"device_brand\": \"Huawei\",\n    \"device_model\": \"example_model\",\n    \"device_screen_resolution\": \"360x720\",\n    \"device_browser\": \"Chrome\",\n    \"geo_country\": \"Russia\",\n    \"geo_city\": \"Zlatoust\"\n   }\n    ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fserverdaun%2Fml_project_sber","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fserverdaun%2Fml_project_sber","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fserverdaun%2Fml_project_sber/lists"}