Code Monkey home page Code Monkey logo

permit-ml's Introduction

Introduction

Building Permit Process Enhancement using Machine Learning

The process to obtain a building permit in San Jose is slow and tedious, primarily due to the fact that a city staff member must review each and every permit application in order for them to be approved. This process could be improved by training a model to handle some, if not most of the review.

Current Problem:

The current system, a building permit in San Jose can take several weeks or even months to obtain, which can prove to be a daunting task for homeowners and contractors. Some municipal agencies provide review services which take place before the application is submitted. However, not only does this require the homeowner or building contractor to physically visit the office to get their application reviewed, but they might even have to visit multiple times if the review process becomes iterative.

Solution:

In order to address these issues, our team has created a Building Permit Prediction Service website which enables users to submit a permit application online and see if their application will be approved, eliminating any need to physically visit the office. Users are able to enter their application details, which consist of specific measurements or qualities of the construction depending on the type of permit desired. Upon submitting the application, the website will provide a prediction for whether or not their application will be approved. The prediction is the result of applying a machine learning model which has been trained on historical permit review data. This website will substantially reduce visits to the city office for reviews for people seeking permits, and will also greatly reduce and streamline the workloads of city employees.

Website URL

http://34.201.136.52:8004/

Architecture Diagram

arch

Technology Stack

  • NodeJS
  • Express
  • MongoDB
  • Amazon Web Services
  • HTML/CSS

Contributors

  1. Arpita Saha
  2. Jiaqi Qin
  3. Matthew Kwong
  4. Pritam Meher

Future Scope:

  • Provide table sorting/filtering, e.g. so that admins can view only applications which are pending.
  • Add useful graphs or statistics to the admin page, to enable more complex analysis.
  • Support other permit application types. For the purposes of providing a proof of concept, we chose to demonstrate a basement permit application, but there are several other permit application types available in San Jose, and the service could easily be extended to support them.
  • Incorporate building plans/blueprints into the machine learning process. Users could be required to upload an image of their building plans or blueprints, computer vision techniques could be used to analyze the image, and the result could be used as a part of the machine learning model.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.