CA5018 Assignment 3

Instruction of Assignment 

Background 

Due to the recent Novel Coronavirus, we may not able to organize the midterm as usual. This assignment was developed to examine the students’ understanding of the course contents and substitute the midterm exam. The students are required to use the real-life data of real estate sales in New York City to develop their model. 

Requirements 

The objective of this assignment is the test the students’ understanding of the course materials and independently develop a computational model for real engineering problems. The students are required to use at least one modeling methods that learned from the course to develop one sale price prediction model and submit the project reports and source codes. The report should have a maximum of 8 pages in length with a single space paragraph and 12 Font size. Here are the major grading criteria for the assignment. 

(1) Introduction and observation of the dataset (20%) (2) The proposed model for price prediction (30%) (3) Insights or conclusions can be drawn from the dataset (35%) (4) Quantitative model or source codes (15%) 

*Note1: As all students have a different background, the students should properly select their method. The selection of methods will not affect the students’ grades. 

*Note2: Grading mainly focuses on how students understand the project and develop a conceptual model of the project. Even if you cannot finish the quantitative model, you still can receive full grades if your model is designed properly. 

*Note3: The students will only receive partial dataset (Use the dataset on Canvas), the model will be tested with other data. 

Appendix: NYC Property Sales 

A year's worth of properties sold on the NYC real estate market 

https://www.kaggle.com/new-york-city/nyc-property-sales/data 

Context 

This dataset is a record of every building or building unit (apartment, etc.) sold in the New York City property market over 12 months. 

Content 

This dataset contains the location, address, type, sale price, and sale date of building units sold. A reference on the trickier fields: 

BOROUGH: A digit code for the borough the property is located in; in order, these are Manhattan (1), Bronx (2), Brooklyn (3), Queens (4), and Staten Island (5). 

BLOCK; LOT: The combination of the borough, block, and lot forms a unique key for property in New York City. Commonly called a BBL. 

BUILDING CLASS AT PRESENT and BUILDING CLASS AT TIME OF SALE: The type of building at various points in time. See the glossary linked to below. 

For further reference on individual fields see the Glossary of Terms. 

(https://www1.nyc.gov/assets/finance/downloads/pdf/07pdf/glossary_rsf071607.pdf ) 

For the building classification codes see the Building Classification Glossary 

(https://www1.nyc.gov/assets/finance/jump/hlpbldgcode.html ) 

Note that because this is a financial transaction dataset, some points need to be kept in mind: 

Many sales occur with a nonsensically small dollar amount: $0 most commonly. These sales are transfers of deeds between parties: for example, parents transferring ownership to their home to a child after moving out for retirement. 

This dataset uses the financial definition of a building/building unit, for tax purposes. In case a single entity owns the building in question, a sale covers the value of the entire building. In case a building is owned piecemeal by its residents (a condominium), a sale refers to a single apartment (or group of apartments) owned by some individual. 

Acknowledgments 

This dataset is a concatenated and slightly cleaned-up version of the New York City Department of Finance's Rolling Sales dataset 

(https://www1.nyc.gov/site/finance/taxes/property-rolling-sales-data.page ). 

Kaggle NYC Property Sales dataset 

(https://www.kaggle.com/new-york-city/nyc-property-sales/data) 

Inspiration 

What can you discover about New York City's real estate by looking at a year's worth of raw transaction records? Can you spot trends in the market, or build a model that predicts sale value in the future?