{"id":22242799,"url":"https://github.com/abdelhakim-gh/pfa-process-mining-fraud-detection","last_synced_at":"2026-04-28T23:01:37.693Z","repository":{"id":250695089,"uuid":"834149289","full_name":"Abdelhakim-gh/PFA-Process-Mining-Fraud-detection","owner":"Abdelhakim-gh","description":"New Frontiers in the Fight against Fraud : The Contribution of Process Mining","archived":false,"fork":false,"pushed_at":"2024-09-13T19:10:29.000Z","size":36765,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-30T09:42:19.838Z","etag":null,"topics":["celonis","data-processing","data-transformation","eda","jupyter-notebook","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Abdelhakim-gh.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":"2024-07-26T14:21:04.000Z","updated_at":"2024-09-13T19:10:32.000Z","dependencies_parsed_at":"2024-09-07T13:55:40.894Z","dependency_job_id":null,"html_url":"https://github.com/Abdelhakim-gh/PFA-Process-Mining-Fraud-detection","commit_stats":null,"previous_names":["abdelhakim-gh/pfa-process-mining-fraud-detection"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdelhakim-gh%2FPFA-Process-Mining-Fraud-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdelhakim-gh%2FPFA-Process-Mining-Fraud-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdelhakim-gh%2FPFA-Process-Mining-Fraud-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdelhakim-gh%2FPFA-Process-Mining-Fraud-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Abdelhakim-gh","download_url":"https://codeload.github.com/Abdelhakim-gh/PFA-Process-Mining-Fraud-detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245449531,"owners_count":20617187,"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":["celonis","data-processing","data-transformation","eda","jupyter-notebook","machine-learning","python"],"created_at":"2024-12-03T04:17:37.623Z","updated_at":"2026-04-28T23:01:37.621Z","avatar_url":"https://github.com/Abdelhakim-gh.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PFA-Process-Mining-Fraud-detection\n\n## Project architecture\n\n\u003cimg src=\"Screens/architecture.png\" alt=\"architecture\" /\u003e\n\n## Description\n\n- **Dataset** : https://www.kaggle.com/datasets/carlosalvite/car-insurance-claims-event-log-for-process-mining?resource=download\n- This event log has been artificially generated and curated to provide a comprehensive view of car insurance claims, allowing users to discover and identify bottlenecks, automation opportunities, conformance issues, reworks, and potential fraudulent cases using any process mining software.\n\n\u003e **Standard Process flow:** _First Notification of Loss (FNOL) → Assign Claim → Claim Decision → Set Reserve → Payment Sent → Close Claim_\n\n\u003cimg src=\"Screens/1.png\" alt=\"image-1\" /\u003e\n\n- **Goal** : a Fraud detection system, combining the power of process mining analysis and machine learning. Analyzed event logs to identify suspicious patterns, then predicted fraud likelihood using ML.\n\n## Features\n\n| Feature Name                      | Description                                                                                                                                | Type        | Example                              |\n| --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ----------- | ------------------------------------ |\n| case_id                           | A unique identifier for each insurance claim case.                                                                                         | Categorical | 000112d5-9d04-450f-820f-3edfc0626cf9 |\n| client                            | The name of the client involved in the claim.                                                                                              | Categorical | Kimberly Collins                     |\n| agent                             | The name of the insurance agent assigned to the claim.                                                                                     | Categorical | Hannah Lopez                         |\n| adjuster                          | The name of the adjuster responsible for handling the claim.                                                                               | Categorical | Joy Simpson                          |\n| claim_amount                      | The monetary value of the insurance claim.                                                                                                 | Numerical   | 9266.19                              |\n| client_age                        | The age of the client involved in the claim.                                                                                               | Numerical   | 60                                   |\n| type_of_policy                    | The type of insurance policy covering the claim. Possible values include: Comprehensive, Collision, etc.                                   | Categorical | Comprehensive                        |\n| car_brand                         | The brand of the car involved in the accident.                                                                                             | Categorical | Hyundai                              |\n| car_model                         | The model of the car involved in the accident.                                                                                             | Categorical | Elantra                              |\n| car_year                          | The manufacturing year of the car involved in the accident.                                                                                | Numerical   | 2021                                 |\n| type_of_accident                  | The type of accident involved in the claim. Possible values include: Head-on, Rear-end, Side-impact, Rollover, etc.                        | Categorical | Head-on                              |\n| user_type                         | Indicates whether the user handling the claim is a human or an RPA (Robotic Process Automation).                                           | Categorical | Human                                |\n| total_activities                  | The total number of activities recorded for the claim process.                                                                             | Numerical   | 6                                    |\n| throughput_duration_days          | The total duration of the claim processing in days.                                                                                        | Numerical   | 31                                   |\n| First Notification of Loss (FNOL) | The sequential order of the activity \"First Notification of Loss\" in the claim process.                                                    | Numerical   | 1                                    |\n| Assign Claim                      | The sequential order of the activity \"Assign Claim\" in the claim process.                                                                  | Numerical   | 2                                    |\n| Claim Decision                    | The sequential order of the activity \"Claim Decision\" in the claim process.                                                                | Numerical   | 3                                    |\n| Set Reserve                       | The sequential order of the activity \"Set Reserve\" in the claim process.                                                                   | Numerical   | 4                                    |\n| Payment Sent                      | The sequential order of the activity \"Payment Sent\" in the claim process.                                                                  | Numerical   | 5                                    |\n| Close Claim                       | The sequential order of the activity \"Close Claim\" in the claim process.                                                                   | Numerical   | 6                                    |\n| State                             | The final status of the claim, indicating whether it was valid, fraudulent or violation. Possible values include: valid, fraud, violation. |             | valid                                |\n\n## Process Mining\n\n- **Process Mining Analysis** : https://academic-celonis-splpne.eu-2.celonis.cloud/package-manager/ui/studio/ui/spaces/aebbc40f-08d6-4a61-98c8-139fdddc5384/packages/1c7bb36f-f7bf-402d-93ce-7b17d5edd05d/nodes/a596af0e-ae07-44d9-96be-62cb7e679638#!/documents/a596af0e-ae07-44d9-96be-62cb7e679638/view/sheets/299b84d5-52eb-4525-93f7-544d92d6b2d0/b/6a0d1817-2b4c-4261-974d-96681dafcbd3\n\n\u003cimg src=\"Screens/2.png\" alt=\"image-2\" /\u003e\n\u003cimg src=\"Screens/3.png\" alt=\"image-3\" /\u003e\n\u003cimg src=\"Screens/4.png\" alt=\"image-4\" /\u003e\n\u003cimg src=\"Screens/5.png\" alt=\"image-5\" /\u003e\n\u003cimg src=\"Screens/6.png\" alt=\"image-6\" /\u003e\n\u003cimg src=\"Screens/7.png\" alt=\"image-7\" /\u003e\n\u003cimg src=\"Screens/8.png\" alt=\"image-8\" /\u003e\n\n## Tools\n\n- Celonis\n- python \u0026 jupyter notebook\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdelhakim-gh%2Fpfa-process-mining-fraud-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabdelhakim-gh%2Fpfa-process-mining-fraud-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdelhakim-gh%2Fpfa-process-mining-fraud-detection/lists"}