{"id":23527975,"url":"https://github.com/nerdingitout/cp4d-bank","last_synced_at":"2025-05-14T10:34:50.379Z","repository":{"id":84626927,"uuid":"301140969","full_name":"nerdingitout/CP4D-bank","owner":"nerdingitout","description":null,"archived":false,"fork":false,"pushed_at":"2021-08-01T12:23:17.000Z","size":103,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-14T10:32:16.241Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nerdingitout.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2020-10-04T13:49:57.000Z","updated_at":"2021-08-01T12:23:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"ac7cb610-74de-44d3-b9c7-1fea07229c07","html_url":"https://github.com/nerdingitout/CP4D-bank","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerdingitout%2FCP4D-bank","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerdingitout%2FCP4D-bank/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerdingitout%2FCP4D-bank/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nerdingitout%2FCP4D-bank/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nerdingitout","download_url":"https://codeload.github.com/nerdingitout/CP4D-bank/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254120972,"owners_count":22018080,"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":[],"created_at":"2024-12-25T20:19:01.185Z","updated_at":"2025-05-14T10:34:50.367Z","avatar_url":"https://github.com/nerdingitout.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CP4D-bank\n## Description\nThis demo aims to automate the banking experience for customers regarding loans on Cloud Pak for Data using Watson Studio, Watson Assistant and Cloud Functions. The project is currently built on the cloud, this documentation aims to provide step-by-step details to implement the same on CP4D on any infrastructure.\n### Features\n- User can interact with the system using a web application or through Watson Assistant\n- Watson Assistant can answer the following questions:\n  - Queries about loans (Loan Predicition, recommending loans and tips to be eligible for loans)\n  - History transactions\n  - Loan Prediction model, using Auto AI, to predict user eligibility for loan.\n## Architecture\n![image](https://user-images.githubusercontent.com/36239840/127770184-9ded48b0-4912-4729-87c9-756436c78b94.png)\n## Demo\nDemo is currently in progress but can be found \u003ca href=\"https://cpd-intelligent-loan-agent-app-masa-anam.eu-gb.mybluemix.net/\"\u003ehere\u003c/a\u003e and the assistant can be found \u003ca href=\"https://web-chat.global.assistant.watson.cloud.ibm.com/preview.html?region=us-south\u0026integrationID=a8294af6-dad3-4c5a-b847-669240a31e82\u0026serviceInstanceID=9735eb72-41b7-4552-9b39-aa1badb7e835\"\u003ehere\u003c/a\u003e.\n## Collect\nIn this project we are using German credit data set: https://online.stat.psu.edu/stat857/node/215/\n\u003c!-- ## Organize\n## Analyze \n## Infuse\n--\u003e\n\n\n# Steps\n\n### Step 1\n1. We found a German credit data set: https://online.stat.psu.edu/stat857/node/215/\n2. We decided to go with the Cloud Pak for Data as a service (Watson Studio). This will help us connect Watson Assistant to our service later.\n3. We uploaded the data set to Watson Studio.\n4. Cleaned the data using data refinery\n5. Built Auto AI Experiment for Loan Prediction. Works with 0.81 accuracy, results are good so far.\n6. Deployed Auto AI in a deployment space.\n\u003c!--\n### Step 2\n1. We built a recommendation system based of the notebook: https://github.com/IBM/product-recommendation-with-watson-ml\n2. In the notebook we edited the first 2 sections to have our data set. \n3. In the prepare data section, we added an ID column to our data. \n4. We are using the columns: --\u003e\n\n### Step 2\nIn this step we mainly focused on building the Loan Assistant with Watson Assistant. Skill can be found in the \"loan-skill.json\" file.\u003cbr\u003e\nThe assistant can do the following:\n- Predict whether user is eligible for loans by asking them a series of questions and then passing into Cloud functions to get results based on the auto ai model we built earlier.\n- Recommend Loans for users based on their data.\n- Users can apply for loans if they are eligible or can ask more information about how to apply for loan or check required documents.\n- Help users with general FAQ questions about loans.\n\n### Step 3\nThe final step in this project is connecting Watson Assistant to the model we built using Cloud functions. \n- On Watson Assistant, we enabled webhooks, and added the HTTP link to the assistant.\n- In the loan prediction dialog node, we enabled the webhook and added the parameters that their values will be processed into the model to get the final results.\n- The cloud functions code that is used as middleware between the assistant and ml model can be found \u003ca href=\"https://github.com/nerdingitout/CP4D-bank/blob/main/cf.py\"\u003ehere\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnerdingitout%2Fcp4d-bank","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnerdingitout%2Fcp4d-bank","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnerdingitout%2Fcp4d-bank/lists"}