Define your scope or domain where the use case is relevant or prevalent?
Affordable and safe housing resources for low-income students and residents in the Ypsilanti
What is your main story?
Which apartment could I afford to rent in a safe neighborhood?
Who are the characters or people in the main story?
Low-income college students who commute to schools at least 3-4 times a week and do part-time jobs after school.
What happens?
The rent in the two college towns, Ann Arbor and Ypsilanti, are higher than that of most cities in Michigan. According to RentCafe, the average rent in Ann Arbor is $1597 and the price is close to the rent of a one-bedroom apartment. Even the affordable neighborhoods charge more than $1000 per month for rent and they are in the suburbs. The average rent in Ypsilanti is $1173, but the area is known to have a higher crime rate than the average of the state. The rent is normally beyond what a college student could afford, and therefore, students often have to balance a few factors among cost, traveling distance, and safety in order to find the most affordable apartment.
Where?
Ann Arbor and Ypsilanti areas
When?
All year round but mostly during school seasons.
Why?
Affordable housing has been an issue for Ann Arbor and Ypsilanti for quite some time. Not only the students’ population but also the lower-income populations are concerned with the increasing rent. A convenient one-stop service that would recommend the most affordable and safe apartment to rent based on a user’s workplace/school, income, debt, desirable safety level would be beneficial. Similar web service like RentCafe, but the ultimate purpose of a commercial service like that is to generate sales. The purpose of our project is to show the scarcity of affordable housing in the area by demonstrating the gap between what people (and in particular students) could afford and what is available on the market.
How?
RentCafe already provides verified data about housing from realtors and property management companies. This project should add on crime stats of the neighborhood as an additional filter. In addition, the project needs to collect large users’ data (students’ data) to show the disparity and scarcity of affordable housing resources in the area.
Exercise if you can break a big story to several smaller stories
- What neighborhoods have apartments that I could afford?
- What neighborhoods are safer than others to rent?
- Are those affordable and safe neighborhoods convenient to my workplace and school?
- How long would it take to commute between apartment, work, and school?
- Does the apartment allow pets? Does the apartment allow sublease?
- Does the apartment have a parking space or garage?
Exercise if you can put the smaller stories into a sequence of stories, or in other words, a sequence of decision-making process.
- Step 1: What neighborhoods have apartments that I could afford?
- Step 2: What neighborhoods are safer than others to rent?
- Step 3: How long would it take to commute between apartment, work, and school?
Exercise if you can extract the important information (age, ethnicity, grade, preference, etc.) from 5W 1H of your main stories.
• User’s monthly income • User’s monthly debt • Users’ workplace address • Users’ school address • Users’ monthly budget for rent • Property’s address • Property’s monthly rent • The crime rate data of the neighborhood where the property is located. • Property’s other features: number of bedrooms, parking, pets, lease term
Explain what you expect from ML applications for each small story (for example, prediction, recommendation, analysis, visualization, search, topic, modeling).
- I expect the ML to search for all available apartments in the selected area.
- I expect the ML to rank the safety level of the apartments based on the crime rate data.
- I expect the ML to calculate how much rent a user could afford based on the calculation of his income, debt, monthly expense.
- I expect the ML to recommend the most convenient apartment within a user’s budget based on the user’s work and school addresses.
- I expect the ML to recommend the safest apartment within a user’s budget.
Story By:
You Li
