Data Science for Driving Urban Intelligence : On the Ground Case Studies in Cities Presented by Amen Ra Mashariki
What keeps City Leadership Up at Night?
Our world is changing...
New Era of City Weather . 18 to 50 inches By 2100 PREDICTED SEA LEVEL RISE Precipitation from heavy storms Every 5 yrs By 2030 70 % since 1958 Frequency of 7.5t floods (~ 2 per millenium)
Urbanization. 64% Increase since 1950 U.S. POPULATION LIVING IN URBAN AREAS - 82% 4-6% Annual growth rate CONSTRUCTION ACTIVITY
Overview Aging Infrastructure. $177B Investment gap 2016 - 2025 ELECTRIC INFRASTRUCTURE $ 270B Replacement cost for gas pipes.
Changing world. Workforce Turnover. Nearly half of the local Government workforce will be nearing retirement age.
Internal External Threats Vulnerabilities Vegetation Pollution RISK Weather Contractors and more...
Healthy Government Economically Vibrant Leaders Are Safe Interested In Outcomes For Diverse Business Opportunities Their Communities… Minimizing traffic congestion and fatalities Sustainability
Precision and Cost- Timely Accuracy Effectiveness Transparent and Collaborative Equitable Ethical What Else? With Data?
Citywide Analytics Offices (National / Global) Worcestire Office London Office of Glasgow, GCC - of Data Analytics Data Analytics City Data Analytics Jenny O’Hagan (WODA), Neill (LODA) – Theo Office , Barcelona Crump Blackwell Chicago San Francisco Los Angeles NYC New Orleans KC Boston
Strong Citywide Analytics Strategy
Urban Intelligence ECOSYSTEM
Analytics Patterns Ranking a list according to certain criteria can enable more efficient use of resources. Prioritizing While the Department of Education must make all schools ADA-compliant, MODA used Where to go first? DOE data to prioritize which schools to renovate first in order to reduce the number of disabled students who needed to be bussed in the meantime. Useful when getting to the worst things earlier can mitigate negative effects. Considering alternative events and measuring the range of their possible outcomes Scenario Analysis can help define the best course of action. As part of the Mayor’s Office of Long Term What if? Planning and Sustainability’s research for a new commercial composting policy, MODA predicted how much waste local businesses would generate under various regulatory thresholds. Useful for planning for a range of possible outcomes. Some processes can be improved by identifying and investigating outliers. For Anomaly Detection What is out of the example, registration records may have a number of files that display unusual ordinary? characteristics. Flagging those records and examining them may reveal procedural “out -of-the- oversight or fraudulent transaction. Useful when investigating the ordinary” is more feasible than examining every case.
Matching can optimally pair two groups against a certain set of constraints. When Matching the appointment scheduler for IDNYC was backlogged with duplicate requests, What goes with what? MODA helped match applicants to times and locations based on indicated preferences. Useful for equitably distributing a limited set of resources. Projects can be planned more effectively when time, material, and costs are Estimating estimated in advance. MODA worked with the Department of Housing How much? Preservation and Development to estimate the resource requirements and a new set of “Enhanced Contractor Review” oversight program outcomes for procedures. Useful for quantifying the costs and benefits of new programs. Targeting can narrow an operational domain to enable better resources allocation. Targeting MODA created a model to help identify buildings that have displayed a pattern of Where to look? unsafe living conditions. This enabled the Tenant Harassment Prevention Task Force to follow up with inspections and enforcement actions when necessary. Useful for identifying a subset for a specific intervention.
Other “analytics” programs… Approach Process Outcome Define, visualize, often Meet goals and KPI Performance using dashboards, and targets Management manage to KPIs Assess a project, Better investment of Evaluation of program or policy resources; Better policy Operations design or results decisions Define and assess Report or memo with Research alternatives using a policy or program Analytics broad range of tools recommendations Publish civic data for Drive transparency and use by the City and the public engagement Open Data public
Is The Problem Solvable With Data?
What Should Your Team look Like?
Case Studies
Over a million buildings in your city. Limited human and financial resources for inspection and canvassing. Accuracy and expediency are crucial. Do not want another person in your city to get sick from Legionella.
Data Science and Location Intelligence Can Help … Without Data Science • There was a 1 in 10 chance of us identifying a building that had a cooling tower. With Data Science • There was an 8 in 10 chance that we could correctly identify a building that had a cooling tower.
FIND THE COOLING TOWERS USING THE SCIENCE OF WHERE
Cooling Towers CITYWIDE OUTREACH EFFORT
Where are Commercial Cooling Tower Systems in New York City? 10 9 ANSWER(S): 8 Avg. Model 7 Success ( out A machine learning model of 10) 6 can correctly identify a 5 building with a cooling tower 8 "No Analytics" 4 out of 10 times, compared to Comparison 3 1 out of 10 times without 2 using analytics. 1 0 Baseline Intuition Stepwise VIF-d no Bldg Cat FLAM Logistic Variable Choice
NYC Current Situation High Market Rate Rents Tenant Harassment Rent Regulation Laws and Deregulation Loopholes
High-Profile Arrests 1578 Union St. 98 Linden St. BBL: 3014000042, BIN: 3037671 BBL: 3033320008, BIN: 3076261 Owner: Daniel Melamed Owner: Israel Brothers
Which Are Predictive? How Can We Test? Likely Conditions Use The Loss Of Rent • Building has rent stabilized apartments Stabilized • Large price difference between market rate and rent stab. Apartments • Recent sale of the buildings TEST • Recent sale of the building As A Proxy followed by construction TEST • 311 Complaints TEST
Possible Indicators Of Tenant Harassment In City Data Recently Recently Illegal Complaints Large Difference Landlords Sold Buildings Sold Building Construction from residents Between Market Taking Tenants Followed By Rate and Rent To Court Intense Regulated Construction Apartments ANALYSIS QUESTION Which of these indicators is more likely to result in the loss of rent regulated units?
DATA SOURCES Which data elements and sources DOF OWNERSHIP are available for MODA to explore? • Sales / Change in Ownership • Names / Addresses of Owners DOB CONSTRUCTION JOBS • Pre-filing Dates DOF CHARGES DATA • Construction Type • Rent Stabilization • HPD Emergency Charges BBL 311 SERVICE REQUESTS • HPD Related JOHN KRAUSS DATA • Construction Related • • Rent Stab unit counts Categories of Complaint Types • Pulled from PDF tax bills • Has counts for each RS BBL from 2007 - 2014
Coordinated GIS Data Integration Apps Desktop APIs
Identifying Trends: Rent Stab Unit Loss Around 5k BBLs (over 10%) experienced unit loss from 2013-2014 Number of BBLs Loosing RS units, colors indicate numbers of units lost, blue=1, purple=2, … In 2014 about 5,000 buildings experienced unit loss. 3,000 of them lost 1 unit, 1000 lost 2 units.
What We Found Buildings with dust or asbestos complaints were 4-7 times more likely to experience unit loss in the following year compared to a random rent stabilized building. • DOB Illegal Work Complaints • Sales Followed By Construction • 311 SR Related To Construction • 311 SR For Air Quality Non-Construction
38
Recommend
More recommend
