https://github.com/viveckh/lilhomie

A Machine Learning Project implemented from scratch which involves web scraping, data engineering, exploratory data analysis and machine learning to predict housing prices in New York Tri-State Area.
https://github.com/viveckh/lilhomie

data-engineering eda housing-price-analysis housing-price-prediction machine-learning machine-learning-projects predictions random-forest-regressor scrapy-crawler spiders trulia web-crawler

Last synced: about 2 months ago
JSON representation

A Machine Learning Project implemented from scratch which involves web scraping, data engineering, exploratory data analysis and machine learning to predict housing prices in New York Tri-State Area.

• Host: GitHub
• URL: https://github.com/viveckh/lilhomie
• Owner: Viveckh
• Created: 2019-02-18T15:07:53.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T01:37:18.000Z (about 2 years ago)
• Last Synced: 2024-10-11T10:39:30.177Z (2 months ago)
• Topics: data-engineering, eda, housing-price-analysis, housing-price-prediction, machine-learning, machine-learning-projects, predictions, random-forest-regressor, scrapy-crawler, spiders, trulia, web-crawler
• Language: Jupyter Notebook
• Homepage:
• Size: 10.5 MB
• Stars: 81
• Watchers: 4
• Forks: 19
• Open Issues: 14
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
### LilHomie - Housing Price Prediction Rapid Prototype

### Author: [(EJ) Vivek Pandey](https://viveckh.com)

LilHomie is a rapid prototyping project that aims to generate housing appraisals to determine values of properties in the New York Tri-state Area. 

This repository contains all the associated work that has been done for the area which includes:

* Web Crawler to gather housing data

* Notebooks associated with data engineering, EDA, and ML Modeling

* Serverless API setup to make predictions off the serialized models

* Web App

### Future Enhancements

* Adding support to crawl and extract through remaining 3 property page formats in Trulia

* Spiders in Web Crawler to extract data from Zillow

* Speeding up the crawler with distributed spiders

* Feeding the ML model with data of properties across the US and making necessary adjustments based on new results, instead of the tri-states properties it is limited to (but this requires the above three enhancements to be done first)

### Questions?

Email the author at [email protected]