What if I could apply a little family data science to help answer the question “Which neighborhood is right for my family?” In other words, I want to rank future neighborhoods of interest in such a way so that the ones on top are guaranteed to satisfy the needs of my family.
Seven years ago, my wife and I moved to Rome, Italy. We moved apartments and neighborhoods quite a number of times just to keep up with the changing demands of a growing family. In two cases, it didn’t take long for us to realize we had moved to a neighborhood that didn’t really suit us.
Looking back over this period, a few factors emerged for those neighborhoods that did work for us, which were curiously missing in those that didn’t.
In this article, I propose a method to rank neighborhoods of interest according to criteria important to us. I then apply this method to automatically rank past and present neighborhoods we’ve lived in in order to see if the ranking reflects our preferences.
I recently read “The Death and Life of Great Italian Cities: A Mobile Phone Data Perspective” which details a study conducted by a group of Italian researchers to measure ‘city liveliness’-metrics focused on urban diversity and urban vitality. Their work is based on the theories and concepts outlined by Jane Jacobs in her seminal book “The Death and Life of Great American Cities.” In her book, Ms. Jacobs proposes four qualities any city neighborhood must have in order to be vibrant and desirable to its residents. The research, and my ranking of neighborhoods, is based on these four qualities.
I wanted to use some of these metrics, but I needed to apply them at the neighborhood level not just the city level as done by the researchers. One idea for doing this is to rely on remote sensing of satellite images. With geospatial platforms such as Google Earth Engine, this is very much doable.
In the sections below, I use Google Earth Engine to compute neighborhood-related features that are based on the “four generators of diversity” proposed by Jane Jacobs. The final ranking for my neighborhoods of interest will be based on these features.
Our newborn loves to sit back in her stroller and listen to the wind move its way through the tree leaves. Our small girls, on the other hand, love the freedom to scoot or bike around without having to worry about cars and trucks running them over. This means that our ideal neighborhood will have a combination of green as well as park areas closed off to traffic.
I rely on the standard Normalized Difference Vegetation Index (NDVI) to calculate a neighborhood’s ‘greenesss’. NDVI works because satellite’s equipped with near-infrared sensors accurately record reflection of solar radiation by green vegetation on the ground.
NDVI is a numerical indicator and can be computed by analyzing satellite images in Google Earth Engine (see Image 1).
Ranking our Rome neighborhoods of interest by their NDVI confirms what we already knew – Trastevere is one of the greenest and also happens to be our favorite neighborhood in Rome.
- Della Vittoria – .33 NDVI
- Trastevere – .25 NDVI
- Ostiense – .23 NDVI
- Testaccio – .19 NDVI
- Prati – .13 NDVI
Multiple Land Use
Neighborhoods that serve multiple functions is another aspect of urban life important to us. It is really great when we can greet the neighbors, pick our favorite flavor at the local ice-cream shop, get a hair-cut and take the kids to the children’s park all within a short walk of our front door. The foot traffic generated by these types of neighborhoods creates an urban vibrancy unlike that experienced in single-use neighborhoods.
Land Use Mix is one of the variables used by the researchers in the paper I referred to earlier . The underlying principle for Land Use Mix was proposed by Jacobs when she suggested a city district should serve more than one primary function, preferably more than two.
The researchers concluded that the city of Rome has a high Land Use Mix. Living here for the past seven years, however, taught us that not all neighborhoods exhibit the same levels of Land Use Mix.
In my quest to pick the perfect neighborhood, I will also calculate Land Use Mix for the neighborhoods we have lived in using the following formula:
where Pi,j refers to the percentage of square footage with land use j in district i, and n is the number of possible land uses. For the purpose of my article, a ‘district’ is synonymous with ‘neighborhood’, which I consider to be equivalent to the Rioni of Rome or the Quarters of Rome. Just like the researchers, I will use a value of n=3 (1=residential, 2=parks/squares/water, 3=businesses/commercial/government). Dedicated single-use neighborhoods will have LUMi equal to zero. When land use is equally divided in all n ways then LUMi will equal one. The higher LUMi, the more mixed the neighborhood’s land use.
Ranking our Rome neighborhoods of interest by their Land Use Mix begins to reveal some interesting characteristics:
- Trastevere .73 LUM
- Della Vittoria .64 LUM
- Testaccio .44 LUM
- Prati .44 LUM
- Ostiense .34 LUM
Neighborhood Block Size
Jacobs believed people didn’t like walking down long blocks, and instead would avoid them at all costs. She believed short blocks offered more navigation options between Point A and B. With short blocks, pedestrian traffic is more easily distributed and this distribution helps create more viable locations for smaller businesses to mix into residential areas.
This observation plays out on the streets of Rome everyday. Neighborhoods composed of mostly small, sometimes quirky shaped blocks are full of small mom-and-pop type stores sitting at the base of multi-level residential buildings.
Not surprisingly, applying the formula for block size in my neighborhoods of interest reveals the following:
- Testaccio .004
- Trastevere .006
- Prati .008
- Della Vittoria .011
- Ostiense .015
Many times numbers simply confirm what our intuition knew all along. In this exercise, I took the principles proposed by Jacobs and the some of the metrics utilized by researchers to rank a set of Roman neighborhoods based on characteristics important to me and my family. I then used Google Earth Engine and remote sensing of satellite images to quantify these characteristics. Having lived in all five neighborhoods of interest, we have strong opinions regarding these neighborhoods and how they compare to one another. Not surprisingly, the final ranking reflects these opinions.
 R. Cervero. Land-use mixing and suburban mobility. University of California Transportation Center, 1989.