Difference between revisions of "GeoEstate"

From Geospatial Analytics and Applications
Jump to navigation Jump to search
Line 1: Line 1:
<div align="center" style="font-size:75px">GeoEstate</div>
+
<div align="center" style="font-size:75px">[[File:GeoEstate_logo.png|center|link=WhereYouGeo|250px]]GeoEstate</div>
  
 
<!------ Main Navigation Bar---->
 
<!------ Main Navigation Bar---->
Line 33: Line 33:
 
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
  
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Group Members
+
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | The Team
 
|}
 
|}
<li>Cerulean Koh Shiliang</li>
+
<br>
<li>Daniel Ang</li>
+
[[File:GeoEstate_team.png|800px]]
<li>Tang Hui Xin</li>
 
  
  
Line 45: Line 44:
 
|}
 
|}
  
Previous research has indicated a relationship between the resale prices of the HDB flats and factors such as the accessibility of the estate and services available in the neighbourhood. Our group questions if this information can be used to predict future HDB resale prices, and if there are other underlying factors yet to be discovered.
+
Landed Property has always been seen as something for the wealthy, with only the top 5% of Singaporean earners being able to afford it. For Singaporeans who aspire to own such Property, there are currently many available options – Terrace Houses, Semi-Detached Houses, Corner Terrace Houses, Detached Houses and many more. Due to fluctuating property prices, it may be difficult for an aspiring landed property owner to properly plan and budget to get their dream house. Furthermore, existing owners may be stressed about when the best time to sell is.
  
We aim to predict future HDB resale prices to fluctuate using a Geographically Weighted Regression Model. This model will be built using factors substantiated using existing research and additional factors that could lead to changes in resale prices.
+
Our project aims to shine light on this by providing an accurate geographically weighted regression model using factors such as location, tenure and type of sale to predict future landed property prices. Now, aspiring owners can filter by location and type of house, and easily see what their dream house would be worth in several years. Alternatively, owners of landed property who plan to sell can see if they should do so sooner or later.
 +
 
 +
Landed Property purchase and sale is a huge financial commitment and we at GeoEstate are committed to ensure that you make the best financial decision for you and your family.
  
  
 
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 
 
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Project Motivation
 
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Project Motivation
 
|}
 
|}
  
 
<br/>
 
<br/>
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Data sources
 +
|}
 +
 +
<table class="wikitable" style="background-color:#FFF; margin: 1em auto;" width="80%; font-size: 15px;">
 +
<tr>
 +
<th> Data </th>
 +
<th> Source </th>
 +
<th> Data Type/Method
 +
</th>
 +
</tr>
 +
<tr>
 +
<td> 2014 Master Plan Planning Subzone (Web) </td>
 +
<td> [https://data.gov.sg/dataset/master-plan-2014-subzone-boundary-web Data.gov.sg] </td>
 +
<td> SHP </td>
 +
</tr>
 +
<tr>
 +
<td> URA Private Residential Property Transactions </td>
 +
<td> [https://www.ura.gov.sg/realEstateIIWeb/transaction/search.action Ura.gov.sg] </td>
 +
<td>
 +
CSV <br/>Data was geocoded using [https://developers.google.com/maps/documentation/geocoding/start Google Geocoding API]
 +
<br/>Postal code was geocoded using [https://docs.onemap.sg/#search OneMap API]
 +
</td>
 +
</tr>
 +
<tr>
 +
<td> Pre-School Locations </td>
 +
<td> [https://data.gov.sg/dataset/pre-schools-location Data.gov.sg] </td>
 +
<td> KML <br/> Converted to Shapefile</td>
 +
</tr>
 +
<tr>
 +
<td> Primary/Secondary School Locations </td>
 +
<td> [https://data.gov.sg/dataset/school-directory-and-information Data.gov.sg] </td>
 +
<td> CSV<br/>Data was geocoded using
 +
[https://docs.onemap.sg/#search OneMap API] </td>
 +
</tr>
 +
<tr>
 +
<td> MRT/LRT Station Locations </td>
 +
<td> [https://www.mytransport.sg/content/dam/datamall/datasets/Geospatial/TrainStation.zip LTA Datamall] <br/>(Direct Download) </td>
 +
<td> SHP </td>
 +
</tr>
 +
<tr>
 +
<td> Supermarket Locations </td>
 +
<td> [https://data.gov.sg/dataset/supermarkets Data.gov.sg] </td>
 +
<td> KML <br/> Converted to Shapefile </td>
 +
</tr>
 +
<tr>
 +
<td> Shopping Mall Locations </td>
 +
<td> [https://en.wikipedia.org/wiki/List_of_shopping_malls_in_Singapore Wikipedia] </td>
 +
<td> Text <br/> Data was converted to Shapefile after geocoding using
 +
[https://docs.onemap.sg/#search OneMap API] </td>
 +
</tr>
 +
<tr>
 +
<td> Park Locations </td>
 +
<td> [https://data.gov.sg/dataset/nparks-parks Data.gov.sg] </td>
 +
<td> KML <br/> Converted to Shapefile </td>
 +
</tr>
 +
<tr>
 +
<td> Sports Facilities Locations </td>
 +
<td> [https://data.gov.sg/dataset/sportsg-sport-facilities Data.gov.sg] </td>
 +
<td> KML <br/> Converted to Shapefile </td>
 +
</tr>
 +
<tr>
 +
<td> Hawker Centre Locations </td>
 +
<td>
 +
Public Food Centres: <br>
 +
1. [https://data.gov.sg/dataset/hawker-centres Data.gov.sg]<br><br>
 +
Private Food Centres: <br>
 +
2. [http://www.kopitiam.biz/search-results/?keywords&zone=allzone&FC=yes&search=Search Kopitam]<br>
 +
3. [https://www.koufu.com.sg/our-brands/food-halls/koufu/ Koufu]<br>
 +
4. [https://www.foodjunction.com/outlets/ Food Junction]<br>
 +
5. [https://foodrepublic.com.sg/food-republic-outlets/ Food Republic]
 +
</td>
 +
<td>
 +
1: KML - Converted to Shapefile <br>
 +
2 - 5: Text - Data scraped from sites and geocoded using [https://docs.onemap.sg/#search OneMap API]
 +
</td>
 +
</tr>
 +
</table>
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Approach
 +
|}
 +
 +
<br>
 +
<br>
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Project Timeline
 +
|}
 +
 +
<br>
 +
<br>
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Project Prototype
 +
|}
 +
 +
<br>
 +
<br>
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Tools & Technology
 +
|}
 +
 +
[[File:GeoEstate_tech_stack.png|1000px]]
 +
 +
{| style="background-color:#ffffff ; margin: 3px 10px 3px 10px; width="80%"|
 +
| style="font-family:Open Sans, Arial, sans-serif; font-size:24px; border-top:solid #ffffff; border-bottom:solid #2DB0AF" width="9999px" | Challenges
 +
|}
 +
 +
 +
<table class="wikitable" style="background-color:#FFF; margin: 1em auto;" width="80%; font-size: 15px;">
 +
<tr>
 +
<th> No. </th>
 +
<th> Key Challenges </th>
 +
<th> Mitigation </th>
 +
</tr>
 +
 +
<tr>
 +
<td> 1. </td>
 +
<td> Unfamiliarity with R, its packages and R Shiny </td>
 +
<td>
 +
# Self-directed learning with online resources such as Datacamp,
 +
# Browsing community forum (Stackoverflow / discuss.onemap) for help
 +
# Looking at official documentation for various packages
 +
</td>
 +
</tr>
 +
 +
<tr>
 +
<td> 2. </td>
 +
<td> Limited oneMap API call for standard account </td>
 +
<td>
 +
# Creation of R script to catch timeout & wait
 +
# Filtering out distinct records to query oneMap to reduce the quantity of duplicated request
 +
</td>
 +
</tr>
 +
</table>

Revision as of 17:52, 19 March 2019

GeoEstate logo.png
GeoEstate

HOME

 

PROPOSAL

 

POSTER

 

APPLICATION

 

RESEARCH PAPER


The Team


GeoEstate team.png


Project Description

Landed Property has always been seen as something for the wealthy, with only the top 5% of Singaporean earners being able to afford it. For Singaporeans who aspire to own such Property, there are currently many available options – Terrace Houses, Semi-Detached Houses, Corner Terrace Houses, Detached Houses and many more. Due to fluctuating property prices, it may be difficult for an aspiring landed property owner to properly plan and budget to get their dream house. Furthermore, existing owners may be stressed about when the best time to sell is.

Our project aims to shine light on this by providing an accurate geographically weighted regression model using factors such as location, tenure and type of sale to predict future landed property prices. Now, aspiring owners can filter by location and type of house, and easily see what their dream house would be worth in several years. Alternatively, owners of landed property who plan to sell can see if they should do so sooner or later.

Landed Property purchase and sale is a huge financial commitment and we at GeoEstate are committed to ensure that you make the best financial decision for you and your family.


Project Motivation


Data sources
Data Source Data Type/Method
2014 Master Plan Planning Subzone (Web) Data.gov.sg SHP
URA Private Residential Property Transactions Ura.gov.sg

CSV
Data was geocoded using Google Geocoding API
Postal code was geocoded using OneMap API

Pre-School Locations Data.gov.sg KML
Converted to Shapefile
Primary/Secondary School Locations Data.gov.sg CSV
Data was geocoded using OneMap API
MRT/LRT Station Locations LTA Datamall
(Direct Download)
SHP
Supermarket Locations Data.gov.sg KML
Converted to Shapefile
Shopping Mall Locations Wikipedia Text
Data was converted to Shapefile after geocoding using OneMap API
Park Locations Data.gov.sg KML
Converted to Shapefile
Sports Facilities Locations Data.gov.sg KML
Converted to Shapefile
Hawker Centre Locations

Public Food Centres:
1. Data.gov.sg

Private Food Centres:
2. Kopitam
3. Koufu
4. Food Junction
5. Food Republic

1: KML - Converted to Shapefile
2 - 5: Text - Data scraped from sites and geocoded using OneMap API

Approach



Project Timeline



Project Prototype



Tools & Technology

GeoEstate tech stack.png

Challenges


No. Key Challenges Mitigation
1. Unfamiliarity with R, its packages and R Shiny
  1. Self-directed learning with online resources such as Datacamp,
  2. Browsing community forum (Stackoverflow / discuss.onemap) for help
  3. Looking at official documentation for various packages
2. Limited oneMap API call for standard account
  1. Creation of R script to catch timeout & wait
  2. Filtering out distinct records to query oneMap to reduce the quantity of duplicated request