Description:

Zillow's Zestimate home valuation has shaken up the U.S. real estate industry since first released 11 years ago. A home is often the largest and most expensive purchase a person makes in his or her lifetime. Ensuring homeowners have a trusted way to monitor this asset is incredibly important. The Zestimate was created to give consumers as much information as possible about homes and the housing market, marking the first-time consumers had access to this type of home value information at no cost. "Zestimates" are estimated home values based on 7.5 million statistical and machine learning models that analyze hundreds of data points on each property. And, by continually improving the median margin of error (from 14% at the onset to 5% today), Zillow has since become established as one of the largest, most trusted marketplaces for real estate information in the U.S. and a leading example of impactful machine learning. This project is the very simplified version of Zillow Prize competition. Zillow Prize was a competition with a one-million-dollar grand prize with the objective to help push the accuracy of the Zestimate even further. Winning algorithms stand to impact the home values of 110M homes across the U.S.

Project You test and compare the following three models. A) Build a regression [module 5] and decision tree [module 7] model that can accurately predict the price of a house based on several predictors (you select appropriate features). B) Use classification [module 6] to model OverallQual (rating 7 and above is considered as class 1, otherwise class zero). Project Deliverables

The following items need to be delivered:

I. Project report:

This is your end-of-project delivery document. It is a document that summarizes different aspects of the project. It includes the following sections:

0. The first page of the document should include a table with a list of the names of the group participants and a summary of the contribution of each team member. 1. Project Goal 2. Overview of data, including data exploration analysis 3. Details of your modeling strategy (feature selection, how/why you choose specific features, optimal hyperparameters, etc.) 4. Estimation of the models performance. It has two subsections: -establishing models (based on the train dataset) and -prediction performance based on the test dataset. The reason to build any model is to be able to use it! In your project, once you have constructed your model, you need to use your model to predict. You must include a subsection to compare your prediction results. To compare models, you may use criteria based on the confusion matrix and/or criteria such as R2_adj, RMSE, and MAE. 5. Insights and conclusions You can include snapshots of your R code and the outputs in the report. You must submit a single document per group in Word format.

II. R codes and script: Submit the commented R-Markdown file (*.html).

III. Presentation Slides:

Finally, you need to prepare a few presentation slides sharing your insights from your project with the board of directors. This should mostly focus on the high-level insights as opposed to technical details. As a part of your submission, you should include a narrated PowerPoint slide. You can easily do this by including your voice recordings in the presentations.

Submit these three items, namely, I-III, as a single zipped file. One Submission per group. The zip file should be named Group_X.zip where X is your group number, e.g., Group_10.zip

Appendix A:

Description of variables (DATA dictionary)

LotArea: Lot size in square feet

OverallQual: Rates the overall material and finish of the house. 10 Very Excellent; 9 Excellent; 8 Very Good; 7 Good; 6 Above Average; 5 Average; 4 Below Average; 3 Fair; 2 Poor; and 1 Very Poor.

YearBuilt: Original construction date

YearRemodAdd: Remodel date (same as construction date if no remodeling or additions)

BsmtFinSF1: Finished square feet

FullBath: Full bathrooms

HalfBath: Half baths

BedroomAbvGr: Number of Bedrooms above the ground

TotRmsAbvGrd: Number of rooms above the ground

Fireplaces: Number of fireplaces

GarageArea: Size of garage in square feet

YrSold: Year sold

SalePrice: The sale price of the property.

Below is the Data sets:

House_Prices

LotArea	OverallQual	YearBuilt	YearRemodAdd	BsmtFinSF1	FullBath	HalfBath	BedroomAbvGr	TotRmsAbvGrd	Fireplaces	GarageArea	YrSold	SalePrice
8450	7	2003	2003	706	2	1	3	8	0	548	2008	208500
9600	6	1976	1976	978	2	0	3	6	1	460	2007	181500
11250	7	2001	2002	486	2	1	3	6	1	608	2008	223500
9550	7	1915	1970	216	1	0	3	7	1	642	2006	140000
14260	8	2000	2000	655	2	1	4	9	1	836	2008	250000
14115	5	1993	1995	732	1	1	1	5	0	480	2009	143000
10084	8	2004	2005	1369	2	0	3	7	1	636	2007	307000
10382	7	1973	1973	859	2	1	3	7	2	484	2009	200000
6120	7	1931	1950	0	2	0	2	8	2	468	2008	129900
7420	5	1939	1950	851	1	0	2	5	2	205	2008	118000
11200	5	1965	1965	906	1	0	3	5	0	384	2008	129500
11924	9	2005	2006	998	3	0	4	11	2	736	2006	345000
12968	5	1962	1962	737	1	0	2	4	0	352	2008	144000
10652	7	2006	2007	0	2	0	3	7	1	840	2007	279500
10920	6	1960	1960	733	1	1	2	5	1	352	2008	157000
6120	7	1929	2001	0	1	0	2	5	0	576	2007	132000
11241	6	1970	1970	578	1	0	2	5	1	480	2010	149000
10791	4	1967	1967	0	2	0	2	6	0	516	2006	90000
13695	5	2004	2004	646	1	1	3	6	0	576	2008	159000
7560	5	1958	1965	504	1	0	3	6	0	294	2009	139000
14215	8	2005	2006	0	3	1	4	9	1	853	2006	325300
7449	7	1930	1950	0	1	0	3	6	1	280	2007	139400
9742	8	2002	2002	0	2	0	3	7	1	534	2008	230000
4224	5	1976	1976	840	1	0	3	6	1	572	2007	129900
8246	5	1968	2001	188	1	0	3	6	1	270	2010	154000
14230	8	2007	2007	0	2	0	3	7	1	890	2009	256300