zhangle59 / workshop-project-submission-template Goto Github PK

[Naming Convention] CourseCode-StartDate-BatchCode-Group_or_Individual-TeamName_or_PersonName-ProjectName.zip

• [MTech Group Project Naming Example] IRS-MR-2019-01-19-IS1PT-GRP-AwsomeSG-HDB_BTO_Recommender.zip

• [MTech Individual Project Naming Example] IRS-MR-2019-07-01-IS1FT-IND-SamGuZhan-HDB_BTO_Process.zip

• [EEP Group Project Naming Example] IRS-MR-2019-03-13-EEP-GRP-AwsomeSG-HDB_BTO_Recommender.zip

• [EEP Individual Project Naming Example] IRS-MR-2019-08-22-EEP-IND-SamGuZhan-HDB_BTO_Process.zip

Online editor for this README.md markdown file

Singapore ranks amongst countries with the highest population density in the world. In a bid to have firm control over long term urban planning, the Singapore government came up with the “Built to Order” (abbreviated BTO) initiative back in 2001. These are new Housing Development Board (HDB) flats tightly controlled by their eligibility and quantity released every year. In more recent years, the modern BTO scheme in Singapore requires a waiting period of 3-4 years, and is generally targeted at young Singaporean couples looking to purchase their first property and set up a family. Nationality and income ceilings are some of the broad filters that determine one’s eligibility for the highly sought after projects.

Our team, comprising of 6 young Singaporeans, all hope to be property owners one day. Many of our peers opt for BTO flats due to their affordability, existence of financial aid from the government, as well as their resale value. However, there often exists a knowledge gap for these young couples during the decision making process and they end up making potentially regretful decisions. We would like to bridge this knowledge gap, and have hence chosen to base our project on creating a recommender system for BTO flats, utilizing the data from recent launches in Tampines, Eunos, Sengkang and Punggol.

Using the techniques imparted to us in lectures, our group first set out to build a sizeable knowledge base via conducting an interview and administering a survey. While building the system, we utilized tools such as Java to scrape real time data from HDB website and transform it into a database, CLIPS to synthesize the rule based reasoning process, and Python to integrate it into an easy to use UI for the everyday user. To add icing on the cake, we even hosted the system on a website so that the everyday user can access it through the click of a link.

Our team had an amazing time working on this project, and hope to share our insights with everyone. Despite a focus on BTO flats, we would recommend it for everybody interested in understanding property market trends for residence or investment purposes. There truly are a wide array of factors behind the decision to invest in a property, and we only wish there was more time to work on the scope and scale of the project.

Note: It is not mandatory for every project member to appear in video presentation; Presentation by one project member is acceptable. More reference video presentations here

<Github File Link> : https://github.com/telescopeuser/Workshop-Project-Submission-Template/blob/master/UserGuide/User%20Guide%20HDB-BTO.pdf

download pre-built virtual machine from http://bit.ly/iss-vm

start iss-vm

open terminal in iss-vm

$ git clone https://github.com/telescopeuser/Workshop-Project-Submission-Template.git

$ source activate iss-env-py2

(iss-env-py2) $ cd Workshop-Project-Submission-Template/SystemCode/clips

(iss-env-py2) $ python app.py

Go to URL using web browser http://0.0.0.0:5000 or http://127.0.0.1:5000

$ sudo apt-get install python-clips clips build-essential libssl-dev libffi-dev python-dev python-pip

$ pip install pyclips flask flask-socketio eventlet simplejson pandas

<Github File Link> : https://github.com/telescopeuser/Workshop-Project-Submission-Template/blob/master/ProjectReport/Project%20Report%20HDB-BTO.pdf

Recommended Sections for Project Report / Paper:

• Executive Summary / Paper Abstract
• Sponsor Company Introduction (if applicable)
• Business Problem Background
• Project Objectives & Success Measurements
• Project Solution (To detail domain modelling & system design.)
• Project Implementation (To detail system development & testing approach.)
• Project Performance & Validation (To prove project objectives are met.)
• Project Conclusions: Findings & Recommendation
• List of Abbreviations (if applicable)
• References (if applicable)

• Results of survey
• Insights derived, which were subsequently used in our system

This Machine Reasoning (MR) course is part of the Analytics and Intelligent Systems and Graduate Certificate in Intelligent Reasoning Systems (IRS) series offered by NUS-ISS.

Lecturer: GU Zhan (Sam)

[email protected]