Electric Vehicle Charger Planning
Electric vehicle charger planning for intra-city travel is complex as it requires multiple data sources on existing charger locations, work and leisure-related trip patterns, points of interest (POI) for deploying new stations, EV ownership populations, power network properties, and sociodemographic features. EV Charger Pro is an interactive tool that creates comprehensive expansion plans with versatile analytics, including charger location optimization, POI assessment, and "Network Science" analytics.
Below is a demonstration of three features of the tool. The ward shades are first chosen to represent the ratio of DC outlets over the population of EV owners in each ward. A DC station is then added and relocated between wards, while the POIs are updated based on the new locations. Lastly, the optimization engine is executed to provide guidance on the ideal wards for the new charger.
On-street Parking Pricing
A highly neglected source of on-street parking occupancy data is parking payment transactions. In contrast to costly, hardly scalable, and infrastructure-invasive sensors, parking payment data is widely accessible with a wealth of information on parking behavior. On the downside, this data does not capture permit-holders, illegal parkers – those who don’t pay at all and those who overstay their payment, and early departers- those who leave earlier than granted.
ParkPlan-Pro is a web-based tool that uses ID-anonymized transaction data from Green-P and developed a parking occupancy prediction model using a Graph Neural Network and other ML benchmarks. We embedded the prediction model into an interactive parking pricing tool that allows parking analysts to test various pricing scenarios. We have so far developed hourly, time-of-day, and progressive pricing models. The tool also includes geojson boundaries of the Green-P parking zones, which were digitally surveyed and geocoded.
Retail Analytics
Retail-Pro is a tool that allows for answering questions such as the following:
How accessible are major grocery retailers to market segments of different income, age, and other socio-demographic features?
How does accessibility to grocery retailers change with the mode of transportation (walking, cycling, driving)?
Which retailer is best for distributing a product targeted at a specific market segment? For example, single parents within a 10-minute walk of a store.
What is the level of competition, defined in terms of spatial overlap in coverage, of major grocery retailers, and how does it change with accessibility?
What retailer provides more equitable access?
Where should retailers locate new stores?