In 2019, 5.34 million existing private homes changed owners, according to data from the National Association of REALTORS®. 89% of sellers were helped by a real estate agent when trading their home. TADA can help both real estate agents and home sellers evaluate the fair market price for selling a home.

Industry

Real Estate

Project Duration and Effort

Two days

Type of Prediction

Regression

Customer Benefits

  1. Quick and accurate home price estimation.
  2. Objective, unbiased price estimation.
  3. Understanding of the parameters influencing the home price.

Problem to solve

A typical home seller in the U.S. in 2017 was 56 years old. They had lived in their house for the last ten years and had a median income of 107 thousand dollars. While the median age of a first time home buyer was 33, and 47 for a repeat buyer, with respectively 80 thousand dollars and 106 thousand dollars of income. The standard home bought was 1,900 square feet in area, was constructed in 1993, and had three bedrooms and two bathrooms. And on average, 88% took a loan to finance their purchase. Needless to say that, for such a substantial debt contracted, the actual price negotiated has to be as close as possible to the fair market value.

We have used TADA with a dataset describing 409 transactions. It is a regression use case. The following information is included for each transaction:

  1. Price per square meter (goal of the prediction),
  2. House street number,
  3. Last transaction date,
  4. House age,
  5. Distance to nearest metro station,
  6. Number of convenience stores,
  7. Latitude,
  8. Longitude.

 

The goal is to see whether TADA can estimate the home selling price accurately. The price estimation has been mostly dependent on the realtor’s evaluations. However, it is precious for a home seller and a realtor to get a quick, independent, objective estimate in a few clicks.

Objectives

  • Create, in a few clicks, an automated tool that estimates home prices.
  • Understand, for a specific transaction date and place, what criteria impact the home price.
  • Get an objective estimation, free of conflict of interest.

 

It raises the following real estate question: 

Can the price of a home be evaluated automatically with accuracy?

Solution

The TADA predictive models are accurate in home prediction with a MAPE of 14% and an R2 of 77%.

In general, a real estate agent participated in 89% of home sales. There is a benefit to being a recent seller as they typically sold their homes for 99% of the listing price. 38% of all sellers described decreasing the asking price at least once. The average home sold was on the market for three weeks. These figures show the pertinence of choosing the right selling price right away because it eases both price negotiations and sale delays.

TADA has selected the following four criteria out of the eight available in the dataset to make its home price evaluations:

  1. The distance to metro station, with a weight of 33% in TADA’s evaluation,
  2. The house age, with a weight of 31% in TADA’s evaluation,
  3. The latitude, with a weight of 27% in TADA’s evaluation,
  4. The transaction date, with a weight of 8% In TADA’s evaluation.

In 2018, 8% of homes were sold by their owners. Owners selling their home by themselves say that getting the right price and selling within the planned length of time was among the most challenging tasks. Finding the right selling price and optimizing it against the time required for selling are challenges. The live predict feature of TADA can help model this.

Live Predict

Customer Benefits

In two days, home sellers, real estate agents, and homebuyers can obtain:

  • An accurate home price evaluation with an R2 of 77%.
  • An immediate “what-if” analysis to make the relationship between the home price and its age and location.